Si Liu

Ruibin Yuan, Yinghao Ma, Yizhi Li et al. · deepmind, mila

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines. Besides, MARBLE offers an easy-to-use, extendable, and reproducible suite for the community, with a clear statement on copyright issues on datasets. Results suggest recently proposed large-scale pre-trained musical language models perform the best in most tasks, with room for further improvement. The leaderboard and toolkit repository are published at https://marble-bm.shef.ac.uk to promote future music AI research.

Hongyang Li, Chonghao Sima, Jifeng Dai et al.

Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches for most autonomous driving algorithms perform detection, segmentation, tracking, etc., in a front or perspective view. As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance. BEV perception inherits several advantages, as representing surrounding scenes in BEV is intuitive and fusion-friendly; and representing objects in BEV is most desirable for subsequent modules as in planning and/or control. The core problems for BEV perception lie in (a) how to reconstruct the lost 3D information via view transformation from perspective view to BEV; (b) how to acquire ground truth annotations in BEV grid; (c) how to formulate the pipeline to incorporate features from different sources and views; and (d) how to adapt and generalize algorithms as sensor configurations vary across different scenarios. In this survey, we review the most recent works on BEV perception and provide an in-depth analysis of different solutions. Moreover, several systematic designs of BEV approach from the industry are depicted as well. Furthermore, we introduce a full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs. At last, we point out the future research directions in this area. We hope this report will shed some light on the community and encourage more research effort on BEV perception. We keep an active repository to collect the most recent work and provide a toolbox for bag of tricks at https://github.com/OpenDriveLab/Birds-eye-view-Perception

Yusheng Zhao, Jinyu Chen, Chen Gao et al.

Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path planning, which, however, has rarely been studied before in literature. In this article, we propose a Target-Driven Structured Transformer Planner (TD-STP) for long-horizon goal-guided and room layout-aware navigation. Specifically, we devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unexplored environments). In addition, we design a Structured Transformer Planner which elegantly incorporates the explored room layout into a neural attention architecture for structured and global planning. Experimental results demonstrate that our TD-STP substantially improves previous best methods' success rate by 2% and 5% on the test set of R2R and REVERIE benchmarks, respectively. Our code is available at https://github.com/YushengZhao/TD-STP .

Shaofei Huang, Zhenwei Shen, Zehao Huang et al.

Monocular 3D lane detection is a challenging task due to its lack of depth information. A popular solution is to first transform the front-viewed (FV) images or features into the bird-eye-view (BEV) space with inverse perspective mapping (IPM) and detect lanes from BEV features. However, the reliance of IPM on flat ground assumption and loss of context information make it inaccurate to restore 3D information from BEV representations. An attempt has been made to get rid of BEV and predict 3D lanes from FV representations directly, while it still underperforms other BEV-based methods given its lack of structured representation for 3D lanes. In this paper, we define 3D lane anchors in the 3D space and propose a BEV-free method named Anchor3DLane to predict 3D lanes directly from FV representations. 3D lane anchors are projected to the FV features to extract their features which contain both good structural and context information to make accurate predictions. In addition, we also develop a global optimization method that makes use of the equal-width property between lanes to reduce the lateral error of predictions. Extensive experiments on three popular 3D lane detection benchmarks show that our Anchor3DLane outperforms previous BEV-based methods and achieves state-of-the-art performances. The code is available at: https://github.com/tusen-ai/Anchor3DLane.

Linjiang Huang, Kaixin Lu, Guanglu Song et al.

In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors. We show that the predicted boxes from teacher detectors are effective medium to transfer knowledge of teacher detectors, which could be either RCNN-based or DETR-based detectors, to train a more accurate and robust DETR model. This new training scheme can easily incorporate the predicted boxes from multiple teacher detectors, each of which provides parallel supervisions to the student DETR. Our strategy introduces no additional parameters and adds negligible computational cost to the original detector during training. During inference, Teach-DETR brings zero additional overhead and maintains the merit of requiring no non-maximum suppression. Extensive experiments show that our method leads to consistent improvement for various DETR-based detectors. Specifically, we improve the state-of-the-art detector DINO with Swin-Large backbone, 4 scales of feature maps and 36-epoch training schedule, from 57.8% to 58.9% in terms of mean average precision on MSCOCO 2017 validation set. Code will be available at https://github.com/LeonHLJ/Teach-DETR.

Luting Wang, Yi Liu, Penghui Du et al.

Open-vocabulary object detection aims to provide object detectors trained on a fixed set of object categories with the generalizability to detect objects described by arbitrary text queries. Previous methods adopt knowledge distillation to extract knowledge from Pretrained Vision-and-Language Models (PVLMs) and transfer it to detectors. However, due to the non-adaptive proposal cropping and single-level feature mimicking processes, they suffer from information destruction during knowledge extraction and inefficient knowledge transfer. To remedy these limitations, we propose an Object-Aware Distillation Pyramid (OADP) framework, including an Object-Aware Knowledge Extraction (OAKE) module and a Distillation Pyramid (DP) mechanism. When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects. The latter introduces global and block distillation for more comprehensive knowledge transfer to compensate for the missing relation information in object distillation. Extensive experiments show that our method achieves significant improvement compared to current methods. Especially on the MS-COCO dataset, our OADP framework reaches $35.6$ mAP$^{\text{N}}_{50}$, surpassing the current state-of-the-art method by $3.3$ mAP$^{\text{N}}_{50}$. Code is released at https://github.com/LutingWang/OADP.

Yue Liao, Aixi Zhang, Miao Lu et al.

The task of Human-Object Interaction~(HOI) detection could be divided into two core problems, i.e., human-object association and interaction understanding. In this paper, we reveal and address the disadvantages of the conventional query-driven HOI detectors from the two aspects. For the association, previous two-branch methods suffer from complex and costly post-matching, while single-branch methods ignore the features distinction in different tasks. We propose Guided-Embedding Network~(GEN) to attain a two-branch pipeline without post-matching. In GEN, we design an instance decoder to detect humans and objects with two independent query sets and a position Guided Embedding~(p-GE) to mark the human and object in the same position as a pair. Besides, we design an interaction decoder to classify interactions, where the interaction queries are made of instance Guided Embeddings (i-GE) generated from the outputs of each instance decoder layer. For the interaction understanding, previous methods suffer from long-tailed distribution and zero-shot discovery. This paper proposes a Visual-Linguistic Knowledge Transfer (VLKT) training strategy to enhance interaction understanding by transferring knowledge from a visual-linguistic pre-trained model CLIP. In specific, we extract text embeddings for all labels with CLIP to initialize the classifier and adopt a mimic loss to minimize the visual feature distance between GEN and CLIP. As a result, GEN-VLKT outperforms the state of the art by large margins on multiple datasets, e.g., +5.05 mAP on HICO-Det. The source codes are available at https://github.com/YueLiao/gen-vlkt.

Si Liu, Chen Gao, Yuan Chen et al.

Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception, including occlusion and long-range perception. In this survey, we provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community. Specifically, we first introduce the architecture and workflow of typical V2X systems, which affords a broader perspective to understand the entire V2X system and the role of CP within it. Then, we thoroughly summarize and analyze existing V2X perception datasets and CP methods. Particularly, we introduce numerous CP methods from various crucial perspectives, including collaboration stages, roadside sensors placement, latency compensation, performance-bandwidth trade-off, attack/defense, pose alignment, etc. Moreover, we conduct extensive experimental analyses to compare and examine current CP methods, revealing some essential and unexplored insights. Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue. Also, we examine methods under different LiDAR ranges. To study the model robustness, we further investigate the effects of various simulated real-world noises on the performance of different CP methods, covering communication latency, lossy communication, localization errors, and mixed noises. In addition, we look into the sim-to-real generalization ability of existing CP methods. At last, we thoroughly discuss issues and challenges, highlighting promising directions for future efforts. Our codes for experimental analysis will be public at https://github.com/memberRE/Collaborative-Perception.

Xinyu Cai, Wentao Jiang, Runsheng Xu et al.

Recently, Vehicle-to-Everything(V2X) cooperative perception has attracted increasing attention. Infrastructure sensors play a critical role in this research field; however, how to find the optimal placement of infrastructure sensors is rarely studied. In this paper, we investigate the problem of infrastructure sensor placement and propose a pipeline that can efficiently and effectively find optimal installation positions for infrastructure sensors in a realistic simulated environment. To better simulate and evaluate LiDAR placement, we establish a Realistic LiDAR Simulation library that can simulate the unique characteristics of different popular LiDARs and produce high-fidelity LiDAR point clouds in the CARLA simulator. Through simulating point cloud data in different LiDAR placements, we can evaluate the perception accuracy of these placements using multiple detection models. Then, we analyze the correlation between the point cloud distribution and perception accuracy by calculating the density and uniformity of regions of interest. Experiments show that when using the same number and type of LiDAR, the placement scheme optimized by our proposed method improves the average precision by 15%, compared with the conventional placement scheme in the standard lane scene. We also analyze the correlation between perception performance in the region of interest and LiDAR point cloud distribution and validate that density and uniformity can be indicators of performance. Both the RLS Library and related code will be released at https://github.com/PJLab-ADG/PCSim.

Le Zhuo, Zhaokai Wang, Baisen Wang et al.

Music is essential when editing videos, but selecting music manually is difficult and time-consuming. Thus, we seek to automatically generate background music tracks given video input. This is a challenging task since it requires music-video datasets, efficient architectures for video-to-music generation, and reasonable metrics, none of which currently exist. To close this gap, we introduce a complete recipe including dataset, benchmark model, and evaluation metric for video background music generation. We present SymMV, a video and symbolic music dataset with various musical annotations. To the best of our knowledge, it is the first video-music dataset with rich musical annotations. We also propose a benchmark video background music generation framework named V-MusProd, which utilizes music priors of chords, melody, and accompaniment along with video-music relations of semantic, color, and motion features. To address the lack of objective metrics for video-music correspondence, we design a retrieval-based metric VMCP built upon a powerful video-music representation learning model. Experiments show that with our dataset, V-MusProd outperforms the state-of-the-art method in both music quality and correspondence with videos. We believe our dataset, benchmark model, and evaluation metric will boost the development of video background music generation. Our dataset and code are available at https://github.com/zhuole1025/SymMV.

Fangxun Shu, Yue Liao, Le Zhuo et al.

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM (l-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structure of s-MLLM by integrating a sparse Mixture of Experts (MoE) architecture into the language model, striking a balance between computational efficiency and model expressiveness. Second, we propose a progressive knowledge transfer strategy to ensure comprehensive knowledge migration. This strategy begins with mimic distillation, where we minimize the Kullback-Leibler (KL) divergence between output distributions to enable the student model to emulate the teacher network's understanding. Following this, we introduce preference distillation via Direct Preference Optimization (DPO), where the key lies in treating l-MLLM as the reference model. During this phase, the s-MLLM's ability to discriminate between superior and inferior examples is significantly enhanced beyond l-MLLM, leading to a better student that surpasses its teacher, particularly in hallucination benchmarks. Extensive experiments demonstrate that LLaVA-MoD outperforms existing models across various multimodal benchmarks while maintaining a minimal number of activated parameters and low computational costs. Remarkably, LLaVA-MoD, with only 2B activated parameters, surpasses Qwen-VL-Chat-7B by an average of 8.8% across benchmarks, using merely 0.3% of the training data and 23% trainable parameters. These results underscore LLaVA-MoD's ability to effectively distill comprehensive knowledge from its teacher model, paving the way for the development of more efficient MLLMs. The code will be available on: https://github.com/shufangxun/LLaVA-MoD.

Zitian Wang, Zehao Huang, Jiahui Fu et al.

3D object detection from multi-view images has drawn much attention over the past few years. Existing methods mainly establish 3D representations from multi-view images and adopt a dense detection head for object detection, or employ object queries distributed in 3D space to localize objects. In this paper, we design Multi-View 2D Objects guided 3D Object Detector (MV2D), which can lift any 2D object detector to multi-view 3D object detection. Since 2D detections can provide valuable priors for object existence, MV2D exploits 2D detectors to generate object queries conditioned on the rich image semantics. These dynamically generated queries help MV2D to recall objects in the field of view and show a strong capability of localizing 3D objects. For the generated queries, we design a sparse cross attention module to force them to focus on the features of specific objects, which suppresses interference from noises. The evaluation results on the nuScenes dataset demonstrate the dynamic object queries and sparse feature aggregation can promote 3D detection capability. MV2D also exhibits a state-of-the-art performance among existing methods. We hope MV2D can serve as a new baseline for future research. Code is available at \url{https://github.com/tusen-ai/MV2D}.

Jingqiu Zhou, Linjiang Huang, Liang Wang et al.

The task of weakly supervised temporal action localization targets at generating temporal boundaries for actions of interest, meanwhile the action category should also be classified. Pseudo-label-based methods, which serve as an effective solution, have been widely studied recently. However, existing methods generate pseudo labels during training and make predictions during testing under different pipelines or settings, resulting in a gap between training and testing. In this paper, we propose to generate high-quality pseudo labels from the predicted action boundaries. Nevertheless, we note that existing post-processing, like NMS, would lead to information loss, which is insufficient to generate high-quality action boundaries. More importantly, transforming action boundaries into pseudo labels is quite challenging, since the predicted action instances are generally overlapped and have different confidence scores. Besides, the generated pseudo-labels can be fluctuating and inaccurate at the early stage of training. It might repeatedly strengthen the false predictions if there is no mechanism to conduct self-correction. To tackle these issues, we come up with an effective pipeline for learning better pseudo labels. Firstly, we propose a Gaussian weighted fusion module to preserve information of action instances and obtain high-quality action boundaries. Second, we formulate the pseudo-label generation as an optimization problem under the constraints in terms of the confidence scores of action instances. Finally, we introduce the idea of $Δ$ pseudo labels, which enables the model with the ability of self-correction. Our method achieves superior performance to existing methods on two benchmarks, THUMOS14 and ActivityNet1.3, achieving gains of 1.9\% on THUMOS14 and 3.7\% on ActivityNet1.3 in terms of average mAP.

Rongyao Fang, Peng Gao, Aojun Zhou et al.

One-to-one matching is a crucial design in DETR-like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed. Several recent works proposed the one-to-many matching mechanism to accelerate training and boost detection performance. We revisit these methods and model them in a unified format of augmenting the object queries. In this paper, we propose two methods that realize one-to-many matching from a different perspective of augmenting images or image features. The first method is One-to-many Matching via Data Augmentation (denoted as DataAug-DETR). It spatially transforms the images and includes multiple augmented versions of each image in the same training batch. Such a simple augmentation strategy already achieves one-to-many matching and surprisingly improves DETR's performance. The second method is One-to-many matching via Feature Augmentation (denoted as FeatAug-DETR). Unlike DataAug-DETR, it augments the image features instead of the original images and includes multiple augmented features in the same batch to realize one-to-many matching. FeatAug-DETR significantly accelerates DETR training and boosts detection performance while keeping the inference speed unchanged. We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and H-Deformable-DETR. Without extra training data, FeatAug-DETR shortens the training convergence periods of Deformable-DETR to 24 epochs and achieves 58.3 AP on COCO val2017 set with Swin-L as the backbone.

Jinyu Chen, Wenguan Wang, Si Liu et al.

Audio-visual navigation is an audio-targeted wayfinding task where a robot agent is entailed to travel a never-before-seen 3D environment towards the sounding source. In this article, we present ORAN, an omnidirectional audio-visual navigator based on cross-task navigation skill transfer. In particular, ORAN sharpens its two basic abilities for a such challenging task, namely wayfinding and audio-visual information gathering. First, ORAN is trained with a confidence-aware cross-task policy distillation (CCPD) strategy. CCPD transfers the fundamental, point-to-point wayfinding skill that is well trained on the large-scale PointGoal task to ORAN, so as to help ORAN to better master audio-visual navigation with far fewer training samples. To improve the efficiency of knowledge transfer and address the domain gap, CCPD is made to be adaptive to the decision confidence of the teacher policy. Second, ORAN is equipped with an omnidirectional information gathering (OIG) mechanism, i.e., gleaning visual-acoustic observations from different directions before decision-making. As a result, ORAN yields more robust navigation behaviour. Taking CCPD and OIG together, ORAN significantly outperforms previous competitors. After the model ensemble, we got 1st in Soundspaces Challenge 2022, improving SPL and SR by 53% and 35% relatively.

Wentao Jiang, Sheng Jin, Wentao Liu et al.

Human pose estimation aims to accurately estimate a wide variety of human poses. However, existing datasets often follow a long-tailed distribution that unusual poses only occupy a small portion, which further leads to the lack of diversity of rare poses. These issues result in the inferior generalization ability of current pose estimators. In this paper, we present a simple yet effective data augmentation method, termed Pose Transformation (PoseTrans), to alleviate the aforementioned problems. Specifically, we propose Pose Transformation Module (PTM) to create new training samples that have diverse poses and adopt a pose discriminator to ensure the plausibility of the augmented poses. Besides, we propose Pose Clustering Module (PCM) to measure the pose rarity and select the "rarest" poses to help balance the long-tailed distribution. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method, especially on rare poses. Also, our method is efficient and simple to implement, which can be easily integrated into the training pipeline of existing pose estimation models.

Luting Wang, Xiaojie Li, Yue Liao et al.

Conventional knowledge distillation (KD) methods for object detection mainly concentrate on homogeneous teacher-student detectors. However, the design of a lightweight detector for deployment is often significantly different from a high-capacity detector. Thus, we investigate KD among heterogeneous teacher-student pairs for a wide application. We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners. Conventional homogeneous KD (homo-KD) methods suffer from such a gap and are hard to directly obtain satisfactory performance for hetero-KD. In this paper, we propose the HEtero-Assists Distillation (HEAD) framework, leveraging heterogeneous detection heads as assistants to guide the optimization of the student detector to reduce this gap. In HEAD, the assistant is an additional detection head with the architecture homogeneous to the teacher head attached to the student backbone. Thus, a hetero-KD is transformed into a homo-KD, allowing efficient knowledge transfer from the teacher to the student. Moreover, we extend HEAD into a Teacher-Free HEAD (TF-HEAD) framework when a well-trained teacher detector is unavailable. Our method has achieved significant improvement compared to current detection KD methods. For example, on the MS-COCO dataset, TF-HEAD helps R18 RetinaNet achieve 33.9 mAP (+2.2), while HEAD further pushes the limit to 36.2 mAP (+4.5).

Zitian Wang, Xuecheng Nie, Xiaochao Qu et al.

In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.

Fangxun Shu, Biaolong Chen, Yue Liao et al.

We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only feed visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consistency. Instead of blindly applying the mask-then-prediction paradigm from MAE, we propose a masked-then-alignment paradigm for efficient video-text alignment. The motivation is that video-text retrieval tasks rely on high-level alignment rather than low-level reconstruction, and multimodal alignment with masked modeling encourages the model to learn a robust and general multimodal representation from incomplete and unstable inputs. Coupling these designs enables efficient end-to-end pre-training: reduce FLOPs (60% off), accelerate pre-training (by 3x), and improve performance. Our MAC achieves state-of-the-art results on various video-text retrieval datasets, including MSR-VTT, DiDeMo, and ActivityNet. Our approach is omnivorous to input modalities. With minimal modifications, we achieve competitive results on image-text retrieval tasks.

Zihan Ding, Tianrui Hui, Junshi Huang et al.

Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets or incorporate additional 2D ConvNets as encoders to extract mixed spatial-temporal features. However, these methods suffer from spatial misalignment or false distractors due to delayed and implicit spatial-temporal interaction occurring in the decoding phase. To tackle these limitations, we propose a Language-Bridged Duplex Transfer (LBDT) module which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase. Concretely, cross-modal attention is performed among the temporal encoder, referring words and the spatial encoder to aggregate and transfer language-relevant motion and appearance information. In addition, we also propose a Bilateral Channel Activation (BCA) module in the decoding phase for further denoising and highlighting the spatial-temporal consistent features via channel-wise activation. Extensive experiments show our method achieves new state-of-the-art performances on four popular benchmarks with 6.8% and 6.9% absolute AP gains on A2D Sentences and J-HMDB Sentences respectively, while consuming around 7x less computational overhead.

Shaofei Huang, Han Li, Yuqing Wang et al.

Audio visual segmentation (AVS) aims to segment the sounding objects for each frame of a given video. To distinguish the sounding objects from silent ones, both audio-visual semantic correspondence and temporal interaction are required. The previous method applies multi-frame cross-modal attention to conduct pixel-level interactions between audio features and visual features of multiple frames simultaneously, which is both redundant and implicit. In this paper, we propose an Audio-Queried Transformer architecture, AQFormer, where we define a set of object queries conditioned on audio information and associate each of them to particular sounding objects. Explicit object-level semantic correspondence between audio and visual modalities is established by gathering object information from visual features with predefined audio queries. Besides, an Audio-Bridged Temporal Interaction module is proposed to exchange sounding object-relevant information among multiple frames with the bridge of audio features. Extensive experiments are conducted on two AVS benchmarks to show that our method achieves state-of-the-art performances, especially 7.1% M_J and 7.6% M_F gains on the MS3 setting.

Xianghao Kong, Wentao Jiang, Jinrang Jia et al.

Vehicle-to-Everything (V2X) collaborative perception is crucial for autonomous driving. However, achieving high-precision V2X perception requires a significant amount of annotated real-world data, which can always be expensive and hard to acquire. Simulated data have raised much attention since they can be massively produced at an extremely low cost. Nevertheless, the significant domain gap between simulated and real-world data, including differences in sensor type, reflectance patterns, and road surroundings, often leads to poor performance of models trained on simulated data when evaluated on real-world data. In addition, there remains a domain gap between real-world collaborative agents, e.g. different types of sensors may be installed on autonomous vehicles and roadside infrastructures with different extrinsics, further increasing the difficulty of sim2real generalization. To take full advantage of simulated data, we present a new unsupervised sim2real domain adaptation method for V2X collaborative detection named Decoupled Unsupervised Sim2Real Adaptation (DUSA). Our new method decouples the V2X collaborative sim2real domain adaptation problem into two sub-problems: sim2real adaptation and inter-agent adaptation. For sim2real adaptation, we design a Location-adaptive Sim2Real Adapter (LSA) module to adaptively aggregate features from critical locations of the feature map and align the features between simulated data and real-world data via a sim/real discriminator on the aggregated global feature. For inter-agent adaptation, we further devise a Confidence-aware Inter-agent Adapter (CIA) module to align the fine-grained features from heterogeneous agents under the guidance of agent-wise confidence maps. Experiments demonstrate the effectiveness of the proposed DUSA approach on unsupervised sim2real adaptation from the simulated V2XSet dataset to the real-world DAIR-V2X-C dataset.

Wentao Jiang, Hao Xiang, Xinyu Cai et al.

Multi-agent cooperative perception is an increasingly popular topic in the field of autonomous driving, where roadside LiDARs play an essential role. However, how to optimize the placement of roadside LiDARs is a crucial but often overlooked problem. This paper proposes an approach to optimize the placement of roadside LiDARs by selecting optimized positions within the scene for better perception performance. To efficiently obtain the best combination of locations, a greedy algorithm based on perceptual gain is proposed, which selects the location that can maximize the perceptual gain sequentially. We define perceptual gain as the increased perceptual capability when a new LiDAR is placed. To obtain the perception capability, we propose a perception predictor that learns to evaluate LiDAR placement using only a single point cloud frame. A dataset named Roadside-Opt is created using the CARLA simulator to facilitate research on the roadside LiDAR placement problem.

Yulu Gao, Chonghao Sima, Shaoshuai Shi et al.

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Although multiple fusion approaches have been proposed, they can be classified into either sparse-only or dense-only fashion based on the feature representation in the fusion module. In this paper, we analyze them in a common taxonomy and thereafter observe two challenges: 1) sparse-only solutions preserve 3D geometric prior and yet lose rich semantic information from the camera, and 2) dense-only alternatives retain the semantic continuity but miss the accurate geometric information from LiDAR. By analyzing these two formulations, we conclude that the information loss is inevitable due to their design scheme. To compensate for the information loss in either manner, we propose Sparse Dense Fusion (SDF), a complementary framework that incorporates both sparse-fusion and dense-fusion modules via the Transformer architecture. Such a simple yet effective sparse-dense fusion structure enriches semantic texture and exploits spatial structure information simultaneously. Through our SDF strategy, we assemble two popular methods with moderate performance and outperform baseline by 4.3% in mAP and 2.5% in NDS, ranking first on the nuScenes benchmark. Extensive ablations demonstrate the effectiveness of our method and empirically align our analysis.

Qiaosong Qi, Le Zhuo, Aixi Zhang et al.

When hearing music, it is natural for people to dance to its rhythm. Automatic dance generation, however, is a challenging task due to the physical constraints of human motion and rhythmic alignment with target music. Conventional autoregressive methods introduce compounding errors during sampling and struggle to capture the long-term structure of dance sequences. To address these limitations, we present a novel cascaded motion diffusion model, DiffDance, designed for high-resolution, long-form dance generation. This model comprises a music-to-dance diffusion model and a sequence super-resolution diffusion model. To bridge the gap between music and motion for conditional generation, DiffDance employs a pretrained audio representation learning model to extract music embeddings and further align its embedding space to motion via contrastive loss. During training our cascaded diffusion model, we also incorporate multiple geometric losses to constrain the model outputs to be physically plausible and add a dynamic loss weight that adaptively changes over diffusion timesteps to facilitate sample diversity. Through comprehensive experiments performed on the benchmark dataset AIST++, we demonstrate that DiffDance is capable of generating realistic dance sequences that align effectively with the input music. These results are comparable to those achieved by state-of-the-art autoregressive methods.

Jinyu Chen, Chen Gao, Erli Meng et al.

Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. In such a paradigm, the sequence model predicts action at each step through a maintained navigation state, which is generally represented as a one-dimensional vector. However, the crucial navigation clues (i.e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured. In this paper, we propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN. Specifically, we utilise the graph-based feature to represent the navigation state instead of the vector-based state. Accordingly, we devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy. Moreover, the Structured Evolving Module (SEM) is proposed to maintain the structured graph-based state during navigation, where the state is gradually evolved to learn the object-level spatial-temporal relationship. The experiments on the R2R and R4R datasets show that the proposed SEvol model improves VLN models' performance by large margins, e.g., +3% absolute SPL accuracy for NvEM and +8% for EnvDrop on the R2R test set.

Zihan Ding, Zi-han Ding, Tianrui Hui et al.

Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image. The previous two-stage approach first extracts segmentation region proposals by an off-the-shelf panoptic segmentation model, then conducts coarse region-phrase matching to ground the candidate regions for each noun phrase. However, the two-stage pipeline usually suffers from the performance limitation of low-quality proposals in the first stage and the loss of spatial details caused by region feature pooling, as well as complicated strategies designed for things and stuff categories separately. To alleviate these drawbacks, we propose a one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination. Thus, our model can exploit sufficient and finer cross-modal semantic correspondence from the supervision of densely annotated pixel-phrase pairs rather than sparse region-phrase pairs. In addition, we also propose a Language-Compatible Pixel Aggregation (LCPA) module to further enhance the discriminative ability of phrase features through multi-round refinement, which selects the most compatible pixels for each phrase to adaptively aggregate the corresponding visual context. Extensive experiments show that our method achieves new state-of-the-art performance on the PNG benchmark with 4.0 absolute Average Recall gains.

Songhao Han, Le Zhuo, Yue Liao et al.

Vision-language models (VLMs) offer a promising paradigm for image classification by comparing the similarity between images and class embeddings. A critical challenge lies in crafting precise textual representations for class names. While previous studies have leveraged recent advancements in large language models (LLMs) to enhance these descriptors, their outputs often suffer from ambiguity and inaccuracy. We attribute this to two primary factors: 1) the reliance on single-turn textual interactions with LLMs, leading to a mismatch between generated text and visual concepts for VLMs; 2) the oversight of the inter-class relationships, resulting in descriptors that fail to differentiate similar classes effectively. In this paper, we propose a novel framework that integrates LLMs and VLMs to find the optimal class descriptors. Our training-free approach develops an LLM-based agent with an evolutionary optimization strategy to iteratively refine class descriptors. We demonstrate our optimized descriptors are of high quality which effectively improves classification accuracy on a wide range of benchmarks. Additionally, these descriptors offer explainable and robust features, boosting performance across various backbone models and complementing fine-tuning-based methods.

Tianrui Hui, Zihan Ding, Junshi Huang et al.

Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a PhraseObject Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.

Runze He, Kai Ma, Linjiang Huang et al.

Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhance the reconstruction of reference details, we introduce the Decoupled Residual ReferAttention (DRRA) module. This module is designed to integrate fine-grained reference features extracted by a detail extractor into the image editing process in a residual way without interfering with the original self-attention. Given that existing datasets are unsuitable for reference-based image editing tasks, particularly due to the difficulty in constructing image triplets that include a reference image, we curate a high-quality dataset, FreeBench, using a newly developed twice-repainting scheme. FreeBench comprises the images before and after editing, detailed editing instructions, as well as a reference image that maintains the identity of the edited object, encompassing tasks such as object addition, replacement, and deletion. By conducting phased training on FreeBench followed by quality tuning, FreeEdit achieves high-quality zero-shot editing through convenient language instructions. We conduct extensive experiments to evaluate the effectiveness of FreeEdit across multiple task types, demonstrating its superiority over existing methods. The code will be available at: https://freeedit.github.io/.

Xiangjian Jiang, Xuecheng Nie, Zitian Wang et al.

Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup. Considering the maturity of the multi-view motion capture system, in this paper, we propose to solve the prior ill-posed problem by leveraging multiple images from different views, thus significantly enhancing the quality of recovered meshes. In particular, we present a novel \textbf{M}ulti-view human body \textbf{M}esh \textbf{T}ranslator (MMT) model for estimating human body mesh with the help of vision transformer. Specifically, MMT takes multi-view images as input and translates them to targeted meshes in a single-forward manner. MMT fuses features of different views in both encoding and decoding phases, leading to representations embedded with global information. Additionally, to ensure the tokens are intensively focused on the human pose and shape, MMT conducts cross-view alignment at the feature level by projecting 3D keypoint positions to each view and enforcing their consistency in geometry constraints. Comprehensive experiments demonstrate that MMT outperforms existing single or multi-view models by a large margin for human mesh recovery task, notably, 28.8\% improvement in MPVE over the current state-of-the-art method on the challenging HUMBI dataset. Qualitative evaluation also verifies the effectiveness of MMT in reconstructing high-quality human mesh. Codes will be made available upon acceptance.

Zitian Wang, Zehao Huang, Yulu Gao et al.

The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.

Penghui Du, Yu Wang, Yifan Sun et al.

Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP.However, two main challenges emerge:(1) A deficiency in concept representation, where the category names in CLIP's text space lack textual and visual knowledge.(2) An overfitting tendency towards base categories, with the open vocabulary knowledge biased towards base categories during the transfer from VLMs to detectors.To address these challenges, we propose the Language Model Instruction (LaMI) strategy, which leverages the relationships between visual concepts and applies them within a simple yet effective DETR-like detector, termed LaMI-DETR.LaMI utilizes GPT to construct visual concepts and employs T5 to investigate visual similarities across categories.These inter-category relationships refine concept representation and avoid overfitting to base categories.Comprehensive experiments validate our approach's superior performance over existing methods in the same rigorous setting without reliance on external training resources.LaMI-DETR achieves a rare box AP of 43.4 on OV-LVIS, surpassing the previous best by 7.8 rare box AP.

Yuanbin Wang, Leyan Zhu, Shaofei Huang et al.

As one of the fundamental functions of autonomous driving system, freespace detection aims at classifying each pixel of the image captured by the camera as drivable or non-drivable. Current works of freespace detection heavily rely on large amount of densely labeled training data for accuracy and robustness, which is time-consuming and laborious to collect and annotate. To the best of our knowledge, we are the first work to explore unsupervised domain adaptation for freespace detection to alleviate the data limitation problem with synthetic data. We develop a cross-modality domain adaptation framework which exploits both RGB images and surface normal maps generated from depth images. A Collaborative Cross Guidance (CCG) module is proposed to leverage the context information of one modality to guide the other modality in a cross manner, thus realizing inter-modality intra-domain complement. To better bridge the domain gap between source domain (synthetic data) and target domain (real-world data), we also propose a Selective Feature Alignment (SFA) module which only aligns the features of consistent foreground area between the two domains, thus realizing inter-domain intra-modality adaptation. Extensive experiments are conducted by adapting three different synthetic datasets to one real-world dataset for freespace detection respectively. Our method performs closely to fully supervised freespace detection methods (93.08 v.s. 97.50 F1 score) and outperforms other general unsupervised domain adaptation methods for semantic segmentation with large margins, which shows the promising potential of domain adaptation for freespace detection.

Gang Zhang, Junnan Chen, Guohuan Gao et al.

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs introduced by the dense feature maps grow quadratically as the perception range increases, making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless, the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work, we propose SAFDNet, a straightforward yet highly effective architecture, tailored for fully sparse 3D object detection. In SAFDNet, an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset, which features long-range detection, verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably, on Argoverse2, SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster, and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3x faster. The code will be available at https://github.com/zhanggang001/HEDNet.

Yue Hu, Juntong Peng, Sifei Liu et al.

Collaborative perception empowers each agent to improve its perceptual ability through the exchange of perceptual messages with other agents. It inherently results in a fundamental trade-off between perception ability and communication cost. To address this bottleneck issue, our core idea is to optimize the collaborative messages from two key aspects: representation and selection. The proposed codebook-based message representation enables the transmission of integer codes, rather than high-dimensional feature maps. The proposed information-filling-driven message selection optimizes local messages to collectively fill each agent's information demand, preventing information overflow among multiple agents. By integrating these two designs, we propose CodeFilling, a novel communication-efficient collaborative perception system, which significantly advances the perception-communication trade-off and is inclusive to both homogeneous and heterogeneous collaboration settings. We evaluate CodeFilling in both a real-world dataset, DAIR-V2X, and a new simulation dataset, OPV2VH+. Results show that CodeFilling outperforms previous SOTA Where2comm on DAIR-V2X/OPV2VH+ with 1,333/1,206 times lower communication volume. Our code is available at https://github.com/PhyllisH/CodeFilling.

Jiahui Fu, Chen Gao, Zitian Wang et al.

Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird's-eye view (BEV) representation space. However, our empirical findings indicate that previous methods have limitations in generating fusion BEV features free from cross-modal conflicts. These conflicts encompass extrinsic conflicts caused by BEV feature construction and inherent conflicts stemming from heterogeneous sensor signals. Therefore, we propose a novel Eliminating Conflicts Fusion (ECFusion) method to explicitly eliminate the extrinsic/inherent conflicts in BEV space and produce improved multi-modal BEV features. Specifically, we devise a Semantic-guided Flow-based Alignment (SFA) module to resolve extrinsic conflicts via unifying spatial distribution in BEV space before fusion. Moreover, we design a Dissolved Query Recovering (DQR) mechanism to remedy inherent conflicts by preserving objectness clues that are lost in the fusion BEV feature. In general, our method maximizes the effective information utilization of each modality and leverages inter-modal complementarity. Our method achieves state-of-the-art performance in the highly competitive nuScenes 3D object detection dataset. The code is released at https://github.com/fjhzhixi/ECFusion.

Shaofei Huang, Zhenwei Shen, Zehao Huang et al.

In this paper, we focus on the challenging task of monocular 3D lane detection. Previous methods typically adopt inverse perspective mapping (IPM) to transform the Front-Viewed (FV) images or features into the Bird-Eye-Viewed (BEV) space for lane detection. However, IPM's dependence on flat ground assumption and context information loss in BEV representations lead to inaccurate 3D information estimation. Though efforts have been made to bypass BEV and directly predict 3D lanes from FV representations, their performances still fall behind BEV-based methods due to a lack of structured modeling of 3D lanes. In this paper, we propose a novel BEV-free method named Anchor3DLane++ which defines 3D lane anchors as structural representations and makes predictions directly from FV features. We also design a Prototype-based Adaptive Anchor Generation (PAAG) module to generate sample-adaptive sparse 3D anchors dynamically. In addition, an Equal-Width (EW) loss is developed to leverage the parallel property of lanes for regularization. Furthermore, camera-LiDAR fusion is also explored based on Anchor3DLane++ to leverage complementary information. Extensive experiments on three popular 3D lane detection benchmarks show that our Anchor3DLane++ outperforms previous state-of-the-art methods. Code is available at: https://github.com/tusen-ai/Anchor3DLane.

Donglin Yang, Zhenfeng Liu, Wentao Jiang et al.

Employing data augmentation methods to enhance perception performance in adverse weather has attracted considerable attention recently. Most of the LiDAR augmentation methods post-process the existing dataset by physics-based models or machine-learning methods. However, due to the limited environmental annotations and the fixed vehicle trajectories in the existing dataset, it is challenging to edit the scene and expand the diversity of traffic flow and scenario. To this end, we propose a simulator-based physical modeling approach to augment LiDAR data in rainy weather in order to improve the perception performance of LiDAR in this scenario. We complete the modeling task of the rainy weather in the CARLA simulator and establish a pipeline for LiDAR data collection. In particular, we pay special attention to the spray and splash rolled up by the wheels of surrounding vehicles in rain and complete the simulation of this special scenario through the Spray Emitter method we developed. In addition, we examine the influence of different weather conditions on the intensity of the LiDAR echo, develop a prediction network for the intensity of the LiDAR echo, and complete the simulation of 4-feat LiDAR point cloud data. In the experiment, we observe that the model augmented by the synthetic data improves the object detection task's performance in the rainy sequence of the Waymo Open Dataset. Both the code and the dataset will be made publicly available at https://github.com/PJLab-ADG/PCSim#rainypcsim.

Yi Liu, Luting Wang, Zongheng Tang et al.

Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical deployment, particularly in resource-constrained environments. This paper addresses the challenge of compressing DETR by leveraging knowledge distillation, a technique that holds promise for maintaining model performance while reducing size. A critical aspect of DETRs' performance is their reliance on queries to interpret object representations accurately. Traditional distillation methods often focus exclusively on positive queries, identified through bipartite matching, neglecting the rich information present in hard-negative queries. Our visual analysis indicates that hard-negative queries, focusing on foreground elements, are crucial for enhancing distillation outcomes. To this end, we introduce a novel Group Query Selection strategy, which diverges from traditional query selection in DETR distillation by segmenting queries based on their Generalized Intersection over Union (GIoU) with ground truth objects, thereby uncovering valuable hard-negative queries for distillation. Furthermore, we present the Knowledge Distillation via Query Selection for DETR (QSKD) framework, which incorporates Attention-Guided Feature Distillation (AGFD) and Local Alignment Prediction Distillation (LAPD). These components optimize the distillation process by focusing on the most informative aspects of the teacher model's intermediate features and output. Our comprehensive experimental evaluation of the MS-COCO dataset demonstrates the effectiveness of our approach, significantly improving average precision (AP) across various DETR architectures without incurring substantial computational costs. Specifically, the AP of Conditional DETR ResNet-18 increased from 35.8 to 39.9.

Hengyuan Zhao, Ziqin Wang, Qixin Sun et al.

Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning. However, efficiently extending these models to accommodate sequential tasks remains challenging. As new tasks arrive, naive model expansion leads to rapid parameter growth, while modifying shared routing components often causes catastrophic forgetting, undermining previously learned knowledge. To address these issues, we propose LLaVA-CMoE, a continual learning framework for LLMs that requires no replay data of previous tasks and ensures both parameter efficiency and robust knowledge retention. Our approach introduces a Probe-Guided Knowledge Extension mechanism, which uses probe experts to dynamically determine when and where new experts should be added, enabling adaptive and minimal parameter expansion tailored to task complexity. Furthermore, we present a Probabilistic Task Locator that assigns each task a dedicated, lightweight router. To handle the practical issue that task labels are unknown during inference, we leverage a VAE-based reconstruction strategy to identify the most suitable router by matching input distributions, allowing automatic and accurate expert allocation. This design mitigates routing conflicts and catastrophic forgetting, enabling robust continual learning without explicit task labels. Extensive experiments on the CoIN benchmark, covering eight diverse VQA tasks, demonstrate that LLaVA-CMoE delivers strong continual learning performance with a compact model size, significantly reducing forgetting and parameter overhead compared to prior methods. These results showcase the effectiveness and scalability of our approach for parameter-efficient continual learning in large language models. Our code will be open-sourced soon.

Linjiang Huang, Rongyao Fang, Aiping Zhang et al.

In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their trained resolutions. To address this issue, we introduce an innovative, training-free approach FouriScale from the perspective of frequency domain analysis. We replace the original convolutional layers in pre-trained diffusion models by incorporating a dilation technique along with a low-pass operation, intending to achieve structural consistency and scale consistency across resolutions, respectively. Further enhanced by a padding-then-crop strategy, our method can flexibly handle text-to-image generation of various aspect ratios. By using the FouriScale as guidance, our method successfully balances the structural integrity and fidelity of generated images, achieving an astonishing capacity of arbitrary-size, high-resolution, and high-quality generation. With its simplicity and compatibility, our method can provide valuable insights for future explorations into the synthesis of ultra-high-resolution images. The code will be released at https://github.com/LeonHLJ/FouriScale.

Shangzhe Di, Zeren Jiang, Si Liu et al.

In this work, we address the task of video background music generation. Some previous works achieve effective music generation but are unable to generate melodious music tailored to a particular video, and none of them considers the video-music rhythmic consistency. To generate the background music that matches the given video, we first establish the rhythmic relations between video and background music. In particular, we connect timing, motion speed, and motion saliency from video with beat, simu-note density, and simu-note strength from music, respectively. We then propose CMT, a Controllable Music Transformer that enables local control of the aforementioned rhythmic features and global control of the music genre and instruments. Objective and subjective evaluations show that the generated background music has achieved satisfactory compatibility with the input videos, and at the same time, impressive music quality. Code and models are available at https://github.com/wzk1015/video-bgm-generation.

Aixi Zhang, Yue Liao, Si Liu et al.

Two-stage methods have dominated Human-Object Interaction (HOI) detection for several years. Recently, one-stage HOI detection methods have become popular. In this paper, we aim to explore the essential pros and cons of two-stage and one-stage methods. With this as the goal, we find that conventional two-stage methods mainly suffer from positioning positive interactive human-object pairs, while one-stage methods are challenging to make an appropriate trade-off on multi-task learning, i.e., object detection, and interaction classification. Therefore, a core problem is how to take the essence and discard the dregs from the conventional two types of methods. To this end, we propose a novel one-stage framework with disentangling human-object detection and interaction classification in a cascade manner. In detail, we first design a human-object pair generator based on a state-of-the-art one-stage HOI detector by removing the interaction classification module or head and then design a relatively isolated interaction classifier to classify each human-object pair. Two cascade decoders in our proposed framework can focus on one specific task, detection or interaction classification. In terms of the specific implementation, we adopt a transformer-based HOI detector as our base model. The newly introduced disentangling paradigm outperforms existing methods by a large margin, with a significant relative mAP gain of 9.32% on HICO-Det. The source codes are available at https://github.com/YueLiao/CDN.

Chen Gao, Yunpeng Chen, Si Liu et al.

Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation. The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner. During searching, the designed adversarial search algorithm does not need to comput any extra metric to evaluate the performance of the searched architecture, and the search paradigm considers the relevance between the two network architectures and improves their mutual balance. Therefore, AdversarialNAS is very efficient and only takes 1 GPU day to search for a superior generative model in the proposed large search space ($10^{38}$). Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of $10.87$ and highly competitive Inception Score of $8.74$ on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of $26.98$ and Inception score of $9.63$ on STL-10. Code is at: \url{https://github.com/chengaopro/AdversarialNAS}.

Yuanbin Wang, Shaofei Huang, Yulu Gao et al.

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language pre-trained models, such as CLIP, have shown their generalization ability in the zero-shot 2D vision tasks, but are still unable to be applied to 3D semantic segmentation directly. In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels. Both feature-level and output-level alignments are conducted between 2D and 3D encoders for effective knowledge transfer. Concretely, a Multi-granularity Cross-modal Feature Alignment (MCFA) module is proposed to align 2D and 3D features from global semantic and local position perspectives for feature-level alignment. For the output level, per-pixel pseudo labels of unseen classes are extracted using the pre-trained CLIP model as supervision for the 3D segmentation model to mimic the behavior of the CLIP image encoder. Extensive experiments are conducted on two popular benchmarks of point cloud segmentation. Our method outperforms significantly previous state-of-the-art methods under zero-shot setting (+29.2% mIoU on SemanticKITTI and 31.8% mIoU on nuScenes), and further achieves promising results in the annotation-free point cloud semantic segmentation setting, showing its great potential for label-efficient learning.

Runze He, Shaofei Huang, Xuecheng Nie et al.

In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with the editing prompt is nontrivial since there exist two significant challenges, including accurate editing of only foreground regions and multi-view consistency given a single-view reference image. To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing, aimed at foreground-only manipulation while preserving the background. For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem among different views in image-driven editing. Extensive experiments show that our CustomNeRF produces precise editing results under various real scenes for both text- and image-driven settings.

Si Liu, Zihan Ding, Jiahui Fu et al.

The objective of the collaborative vehicle-to-everything perception task is to enhance the individual vehicle's perception capability through message communication among neighboring traffic agents. Previous methods focus on achieving optimal performance within bandwidth limitations and typically adopt BEV maps as the basic collaborative message units. However, we demonstrate that collaboration with dense representations is plagued by object feature destruction during message packing, inefficient message aggregation for long-range collaboration, and implicit structure representation communication. To tackle these issues, we introduce a brand new message unit, namely point cluster, designed to represent the scene sparsely with a combination of low-level structure information and high-level semantic information. The point cluster inherently preserves object information while packing messages, with weak relevance to the collaboration range, and supports explicit structure modeling. Building upon this representation, we propose a novel framework V2X-PC for collaborative perception. This framework includes a Point Cluster Packing (PCP) module to keep object feature and manage bandwidth through the manipulation of cluster point numbers. As for effective message aggregation, we propose a Point Cluster Aggregation (PCA) module to match and merge point clusters associated with the same object. To further handle time latency and pose errors encountered in real-world scenarios, we propose parameter-free solutions that can adapt to different noisy levels without finetuning. Experiments on two widely recognized collaborative perception benchmarks showcase the superior performance of our method compared to the previous state-of-the-art approaches relying on BEV maps.

Jingqiu Zhou, Lue Fan, Xuesong Chen et al.

In this paper, we present GaussianPainter, the first method to paint a point cloud into 3D Gaussians given a reference image. GaussianPainter introduces an innovative feed-forward approach to overcome the limitations of time-consuming test-time optimization in 3D Gaussian splatting. Our method addresses a critical challenge in the field: the non-uniqueness problem inherent in the large parameter space of 3D Gaussian splatting. This space, encompassing rotation, anisotropic scales, and spherical harmonic coefficients, introduces the challenge of rendering similar images from substantially different Gaussian fields. As a result, feed-forward networks face instability when attempting to directly predict high-quality Gaussian fields, struggling to converge on consistent parameters for a given output. To address this issue, we propose to estimate a surface normal for each point to determine its Gaussian rotation. This strategy enables the network to effectively predict the remaining Gaussian parameters in the constrained space. We further enhance our approach with an appearance injection module, incorporating reference image appearance into Gaussian fields via a multiscale triplane representation. Our method successfully balances efficiency and fidelity in 3D Gaussian generation, achieving high-quality, diverse, and robust 3D content creation from point clouds in a single forward pass.

Le Zhuo, Songhao Han, Yuandong Pu et al.

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning, text rendering, and multimodal reasoning for factual fidelity. To address this, we present the first comprehensive, systematic investigation of this domain, encompassing data construction, model training, and an evaluation benchmark. First, we construct a large-scale dataset of 1.3 million high-quality structured image pairs derived from executable drawing programs and augmented with chain-of-thought reasoning annotations. Building on it, we train a unified model that integrates a VLM with FLUX.1 Kontext via a lightweight connector for enhanced multimodal understanding. A three-stage training curriculum enables progressive feature alignment, knowledge infusion, and reasoning-augmented generation, further boosted by an external reasoner at inference time. Finally, we introduce StructBench, a novel benchmark for generation and editing with over 1,700 challenging instances, and an accompanying evaluation metric, StructScore, which employs a multi-round Q\&A protocol to assess fine-grained factual accuracy. Evaluations of 15 models reveal that even leading closed-source systems remain far from satisfactory. Our model attains strong editing performance, and inference-time reasoning yields consistent gains across diverse architectures. By releasing the dataset, model, and benchmark, we aim to advance unified multimodal foundations for structured visuals.