Chunhua Shen

Wenqiang Zhang, Zilong Huang, Guozhong Luo et al. · deepmind, tencent-ai

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \textbf{To}ken \textbf{P}yramid Vision Trans\textbf{former} (\textbf{TopFormer}). The proposed \textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that our method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency. On the ADE20K dataset, TopFormer achieves 5\% higher accuracy in mIoU than MobileNetV3 with lower latency on an ARM-based mobile device. Furthermore, the tiny version of TopFormer achieves real-time inference on an ARM-based mobile device with competitive results. The code and models are available at: https://github.com/hustvl/TopFormer

Wei Yin, Chi Zhang, Hao Chen et al. · tencent-ai

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity. Meanwhile, SOTA monocular methods trained on large mixed datasets achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. In this work, we show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Equipped with our module, monocular models can be stably trained with over 8 million images with thousands of camera models, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Experiments demonstrate SOTA performance of our method on 7 zero-shot benchmarks. Notably, our method won the championship in the 2nd Monocular Depth Estimation Challenge. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. The potential benefits extend to downstream tasks, which can be significantly improved by simply plugging in our model. For example, our model relieves the scale drift issues of monocular-SLAM (Fig. 1), leading to high-quality metric scale dense mapping. The code is available at https://github.com/YvanYin/Metric3D.

Libo Sun, Jia-Wang Bian, Huangying Zhan et al. · bytedance, oxford

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl

Weijia Wu, Yuzhong Zhao, Hao Chen et al.

Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module. Training the decoder only needs less than 1% (around 100 images) manually labeled images, enabling the generation of an infinitely large annotated dataset. Then these synthetic data can be used for training various perception models for downstream tasks. To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic segmentation, instance segmentation, and depth estimation. Notably, it achieves 1) state-of-the-art results on semantic segmentation and instance segmentation; 2) significantly more robust on domain generalization than using the real data alone; and state-of-the-art results in zero-shot segmentation setting; and 3) flexibility for efficient application and novel task composition (e.g., image editing). The project website and code can be found at https://weijiawu.github.io/DatasetDM_page/ and https://github.com/showlab/DatasetDM, respectively

Choubo Ding, Guansong Pang, Chunhua Shen

Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc. These anomaly examples provide valuable knowledge about the application-specific abnormality, enabling significantly improved detection of similar anomalies in some recent models. However, those anomalies seen during training often do not illustrate every possible class of anomaly, rendering these models ineffective in generalizing to unseen anomaly classes. This paper tackles open-set supervised anomaly detection, in which we learn detection models using the anomaly examples with the objective to detect both seen anomalies (`gray swans') and unseen anomalies (`black swans'). We propose a novel approach that learns disentangled representations of abnormalities illustrated by seen anomalies, pseudo anomalies, and latent residual anomalies (i.e., samples that have unusual residuals compared to the normal data in a latent space), with the last two abnormalities designed to detect unseen anomalies. Extensive experiments on nine real-world anomaly detection datasets show superior performance of our model in detecting seen and unseen anomalies under diverse settings. Code and data are available at: https://github.com/choubo/DRA.

Wen Wang, Yan Jiang, Kangyang Xie et al.

Large-scale text-to-image diffusion models achieve unprecedented success in image generation and editing. However, how to extend such success to video editing is unclear. Recent initial attempts at video editing require significant text-to-video data and computation resources for training, which is often not accessible. In this work, we propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video. At the core of our method is a null-text inversion module for text-to-video alignment, a cross-frame modeling module for temporal consistency, and a spatial regularization module for fidelity to the original video. Without any training, we leverage the dynamic nature of the attention mechanism to enable bi-directional temporal modeling at test time. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos. Code is made available at \url{https://github.com/baaivision/vid2vid-zero}.

Jun Wang, Ying Cui, Dongyan Guo et al.

Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs. Two essential blocks Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the short-range and long-range structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with highly detailed geometries. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods by a large margin on popular benchmarks like Completion3D and PCN. Code is available at: https://github.com/ohhhyeahhh/PointAttN

Yuliang Liu, Jiaxin Zhang, Dezhi Peng et al.

End-to-end scene text spotting has made significant progress due to its intrinsic synergy between text detection and recognition. Previous methods commonly regard manual annotations such as horizontal rectangles, rotated rectangles, quadrangles, and polygons as a prerequisite, which are much more expensive than using single-point. Our new framework, SPTS v2, allows us to train high-performing text-spotting models using a single-point annotation. SPTS v2 reserves the advantage of the auto-regressive Transformer with an Instance Assignment Decoder (IAD) through sequentially predicting the center points of all text instances inside the same predicting sequence, while with a Parallel Recognition Decoder (PRD) for text recognition in parallel, which significantly reduces the requirement of the length of the sequence. These two decoders share the same parameters and are interactively connected with a simple but effective information transmission process to pass the gradient and information. Comprehensive experiments on various existing benchmark datasets demonstrate the SPTS v2 can outperform previous state-of-the-art single-point text spotters with fewer parameters while achieving 19$\times$ faster inference speed. Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations. Such an attempt provides a significant opportunity for scene text spotting applications beyond the realms of existing paradigms. Code is available at: https://github.com/Yuliang-Liu/SPTSv2.

Wei Yin, Jianming Zhang, Oliver Wang et al.

Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes mainly due to limited training data. Thus, researchers have built large-scale relative depth datasets that are much easier to collect. However, existing relative depth estimation models often fail to recover accurate 3D scene shapes due to the unknown depth shift caused by training with the relative depth data. We tackle this problem here and attempt to estimate accurate scene shapes by training on large-scale relative depth data, and estimating the depth shift. To do so, we propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image, and then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes. As the two modules are trained separately, we do not need strictly paired training data. In addition, we propose an image-level normalized regression loss and a normal-based geometry loss to improve training with relative depth annotation. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot evaluation. Code is available at: https://git.io/Depth

Yuzhong Zhao, Qixiang Ye, Weijia Wu et al.

Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative prompt model (GenPromp), defining the first generative pipeline to localize less discriminative object parts by formulating WSOL as a conditional image denoising procedure. During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings. During inference, enPromp combines the representative embeddings with discriminative embeddings (queried from an off-the-shelf vision-language model) for both representative and discriminative capacity. The combined embeddings are finally used to generate multi-scale high-quality attention maps, which facilitate localizing full object extent. Experiments on CUB-200-2011 and ILSVRC show that GenPromp respectively outperforms the best discriminative models by 5.2% and 5.6% (Top-1 Loc), setting a solid baseline for WSOL with the generative model. Code is available at https://github.com/callsys/GenPromp.

Bowen Zhang, Liyang Liu, Minh Hieu Phan et al.

This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}. In this study, we introduce a novel Attention-to-Mask (\atm) module to design a lightweight decoder effective for plain ViT. The proposed ATM converts the global attention map into semantic masks for high-quality segmentation results. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5\%$ of the computational cost. For the encoder, we address the concern of the relatively high computational cost in the ViT-based encoders and propose a \emph{Shrunk++} structure that incorporates edge-aware query-based down-sampling (EQD) and query-based upsampling (QU) modules. The Shrunk++ structure reduces the computational cost of the encoder by up to $50\%$ while maintaining competitive performance. Furthermore, we propose to adapt SegViT for continual semantic segmentation, demonstrating nearly zero forgetting of previously learned knowledge. Experiments show that our proposed SegViTv2 surpasses recent segmentation methods on three popular benchmarks including ADE20k, COCO-Stuff-10k and PASCAL-Context datasets. The code is available through the following link: \url{https://github.com/zbwxp/SegVit}.

Hanxi Li, Jianfei Hu, Bo Li et al.

In this work, by re-examining the "matching" nature of Anomaly Detection (AD), we propose a new AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those "global nearest neighbors", by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its "local nearest neighbor" and the "non-background" probability. The proposed method is termed "Cascade Patch Retrieval" (CPR) in this work. Different from the conventional patch-matching-based AD algorithms, CPR selects proper "targets" (reference images and locations) before "shooting" (patch-matching). On the well-acknowledged MVTec AD, BTAD and MVTec-3D AD datasets, the proposed algorithm consistently outperforms all the comparing SOTA methods by remarkable margins, measured by various AD metrics. Furthermore, CPR is extremely efficient. It runs at the speed of 113 FPS with the standard setting while its simplified version only requires less than 1 ms to process an image at the cost of a trivial accuracy drop. The code of CPR is available at https://github.com/flyinghu123/CPR.

Chengzhi Lin, Ancong Wu, Junwei Liang et al. · cmu, tencent-ai

Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the ``Video-Text Correspondence Ambiguity'' problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (\textit{e.g.}, object to entity and action to verb). It is difficult for these methods to alleviate the video-text correspondence ambiguity by describing a video using only one single feature, which is required to be matched with multiple different text features at the same time. To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features. Given a query text, the similarity is determined by the most similar prototype to find correspondence in the video, which is termed text-adaptive matching. To learn diverse prototypes for representing the rich information in videos, we propose a variance loss to encourage different prototypes to attend to different contents of the video. Our method outperforms state-of-the-art methods on four public video retrieval datasets.

Weijia Wu, Yuanqiang Cai, Chunhua Shen et al.

Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods typically follow the tracking-by-match paradigm and develop sophisticated pipelines. In this paper, rooted in Transformer sequence modeling, we propose a simple, but effective end-to-end video text DEtection, Tracking, and Recognition framework (TransDETR). TransDETR mainly includes two advantages: 1) Different from the explicit match paradigm in the adjacent frame, TransDETR tracks and recognizes each text implicitly by the different query termed text query over long-range temporal sequence (more than 7 frames). 2) TransDETR is the first end-to-end trainable video text spotting framework, which simultaneously addresses the three sub-tasks (e.g., text detection, tracking, recognition). Extensive experiments in four video text datasets (i.e.,ICDAR2013 Video, ICDAR2015 Video, Minetto, and YouTube Video Text) are conducted to demonstrate that TransDETR achieves state-of-the-art performance with up to around 8.0% improvements on video text spotting tasks. The code of TransDETR can be found at https://github.com/weijiawu/TransDETR.

Mingbao Lin, Mengzhao Chen, Yuxin Zhang et al.

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing improved image recognition performance with various computational costs. Here, the trained ViT model, termed super vision transformer (SuperViT), is empowered with the versatile ability to solve incoming patches of multiple sizes as well as preserve informative tokens with multiple keeping rates (the ratio of keeping tokens) to achieve good hardware efficiency for inference, given that the available hardware resources often change from time to time. Experimental results on ImageNet demonstrate that our SuperViT can considerably reduce the computational costs of ViT models with even performance increase. For example, we reduce 2x FLOPs of DeiT-S while increasing the Top-1 accuracy by 0.2% and 0.7% for 1.5x reduction. Also, our SuperViT significantly outperforms existing studies on efficient vision transformers. For example, when consuming the same amount of FLOPs, our SuperViT surpasses the recent state-of-the-art (SOTA) EViT by 1.1% when using DeiT-S as their backbones. The project of this work is made publicly available at https://github.com/lmbxmu/SuperViT.

Muzhi Zhu, Hengtao Li, Hao Chen et al. · cmu

Current closed-set instance segmentation models rely on pre-defined class labels for each mask during training and evaluation, largely limiting their ability to detect novel objects. Open-world instance segmentation (OWIS) models address this challenge by detecting unknown objects in a class-agnostic manner. However, previous OWIS approaches completely erase category information during training to keep the model's ability to generalize to unknown objects. In this work, we propose a novel training mechanism termed SegPrompt that uses category information to improve the model's class-agnostic segmentation ability for both known and unknown categories. In addition, the previous OWIS training setting exposes the unknown classes to the training set and brings information leakage, which is unreasonable in the real world. Therefore, we provide a new open-world benchmark closer to a real-world scenario by dividing the dataset classes into known-seen-unseen parts. For the first time, we focus on the model's ability to discover objects that never appear in the training set images. Experiments show that SegPrompt can improve the overall and unseen detection performance by 5.6% and 6.1% in AR on our new benchmark without affecting the inference efficiency. We further demonstrate the effectiveness of our method on existing cross-dataset transfer and strongly supervised settings, leading to 5.5% and 12.3% relative improvement.

Yuting Gao, Jinfeng Liu, Zihan Xu et al. · tencent-ai

Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real scenarios, this assumption can be difficult to hold: the text description, obtained by crawling the affiliated metadata of the image, often suffers from the semantic mismatch and the mutual compatibility. To address these issues, we introduce PyramidCLIP, which constructs an input pyramid with different semantic levels for each modality, and aligns visual elements and linguistic elements in the form of hierarchy via peer-level semantics alignment and cross-level relation alignment. Furthermore, we soften the loss of negative samples (unpaired samples) so as to weaken the strict constraint during the pre-training stage, thus mitigating the risk of forcing the model to distinguish compatible negative pairs. Experiments on five downstream tasks demonstrate the effectiveness of the proposed PyramidCLIP. In particular, with the same amount of 15 million pre-training image-text pairs, PyramidCLIP exceeds CLIP on ImageNet zero-shot classification top-1 accuracy by 10.6%/13.2%/10.0% with ResNet50/ViT-B32/ViT-B16 based image encoder respectively. When scaling to larger datasets, PyramidCLIP achieves the state-of-the-art results on several downstream tasks. In particular, the results of PyramidCLIP-ResNet50 trained on 143M image-text pairs surpass that of CLIP using 400M data on ImageNet zero-shot classification task, significantly improving the data efficiency of CLIP.

Junwei Liang, Enwei Zhang, Jun Zhang et al. · cmu, tencent-ai

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valuable how to train a single model that can perform well across multiple datasets. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss, aiming to learn robust representations for action recognition. In particular, the informative loss maximizes the expressiveness of the feature embedding while the projection loss for each dataset mines the intrinsic relations between classes across datasets. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2 datasets. Extensive experimental results show that our method can consistently improve state-of-the-art performance. Code and models are released.

Wejia Wu, Zhuang Li, Jiahong Li et al.

Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. The code can be found at github.com/weijiawu/CoText.

Chi Zhang, Wei Yin, Zhibin Wang et al. · tencent-ai

In this paper, we address monocular depth estimation with deep neural networks. To enable training of deep monocular estimation models with various sources of datasets, state-of-the-art methods adopt image-level normalization strategies to generate affine-invariant depth representations. However, learning with image-level normalization mainly emphasizes the relations of pixel representations with the global statistic in the images, such as the structure of the scene, while the fine-grained depth difference may be overlooked. In this paper, we propose a novel multi-scale depth normalization method that hierarchically normalizes the depth representations based on spatial information and depth distributions. Compared with previous normalization strategies applied only at the holistic image level, the proposed hierarchical normalization can effectively preserve the fine-grained details and improve accuracy. We present two strategies that define the hierarchical normalization contexts in the depth domain and the spatial domain, respectively. Our extensive experiments show that the proposed normalization strategy remarkably outperforms previous normalization methods, and we set new state-of-the-art on five zero-shot transfer benchmark datasets.

Yulei Qin, Xingyu Chen, Chao Chen et al.

Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the ``realistic" prototype. Then, the intra-class distance between web instances and ``realistic" prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.

Peng-Tao Jiang, Yuqi Yang, Yang Cao et al.

Traffic scene perception in computer vision is a critically important task to achieve intelligent cities. To date, most existing datasets focus on autonomous driving scenes. We observe that the models trained on those driving datasets often yield unsatisfactory results on traffic monitoring scenes. However, little effort has been put into improving the traffic monitoring scene understanding, mainly due to the lack of specific datasets. To fill this gap, we introduce a specialized traffic monitoring dataset, termed TSP6K, containing images from the traffic monitoring scenario, with high-quality pixel-level and instance-level annotations. The TSP6K dataset captures more crowded traffic scenes with several times more traffic participants than the existing driving scenes. We perform a detailed analysis of the dataset and comprehensively evaluate previous popular scene parsing methods, instance segmentation methods and unsupervised domain adaption methods. Furthermore, considering the vast difference in instance sizes, we propose a detail refining decoder for scene parsing, which recovers the details of different semantic regions in traffic scenes owing to the proposed TSP6K dataset. Experiments show its effectiveness in parsing the traffic monitoring scenes. Code and dataset are available at https://github.com/PengtaoJiang/TSP6K.

Liyang Li, Muzhi Zhu, Zhiyue Zhao et al.

Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passive understanding of pre-collected observations. We introduce Target Viewpoint Reproduction (TVR) -- an active task where an agent adjusts its viewpoint in a 3D environment until its observation matches a given target image -- and TVRBench, an indoor-simulation benchmark spanning scene scale and target-view visual richness. TVR is far from solved: on the evaluation split, the strongest open-source and closed-source models reach only 7.8% and 12.0% success. Fine-grained analysis identifies two consistent bottlenecks: off-the-shelf models struggle with multi-turn visual history, and performance drops sharply when viewpoint reproduction requires body translation rather than in-place rotation, exposing a gap in mapping spatial discrepancies to embodied movement. To study reducing this gap, we build a unified TVR post-training framework covering expert-trajectory SFT, rationale-supervised CoT-SFT, offline Single-turn GRPO, and on-policy Multi-turn GRPO from live simulator rollouts. Visual-action SFT supplies the main gain, raising a 9B open-source model to 50.8% success; Multi-turn GRPO provides targeted multi-room refinement and reaches 51.4% overall, while CoT supervision and Single-turn GRPO degrade closed-loop performance. These results establish TVRBench as a testbed for measuring and training foundation models that actively perceive and act in 3D environments. Our code, data, and models are available at https://github.com/aim-uofa/TVRBench.

Xinlong Wang, Wen Wang, Yue Cao et al.

In-context learning, as a new paradigm in NLP, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. But in computer vision, the difficulties for in-context learning lie in that tasks vary significantly in the output representations, thus it is unclear how to define the general-purpose task prompts that the vision model can understand and transfer to out-of-domain tasks. In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images. With this idea, our training process is extremely simple, which performs standard masked image modeling on the stitch of input and output image pairs. This makes the model capable of performing tasks conditioned on visible image patches. Thus, during inference, we can adopt a pair of input and output images from the same task as the input condition, to indicate which task to perform. Without bells and whistles, our generalist Painter can achieve competitive performance compared to well-established task-specific models, on seven representative vision tasks ranging from high-level visual understanding to low-level image processing. In addition, Painter significantly outperforms recent generalist models on several challenging tasks.

Yanda Li, Chi Zhang, Gang Yu et al. · tencent-ai

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and textual modalities effectively while comprehending human instructions. Current methodologies often rely on annotations derived from benchmark datasets to construct image-dialogue datasets for training purposes, akin to instruction tuning in LLMs. However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models. In an effort to mitigate these limitations, we propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models to yield a diverse and controllable dataset with varied image content. Additionally, datasets can be arbitrarily scaled. This not only provides greater flexibility compared to existing methodologies but also significantly enhances several model capabilities. Our research includes comprehensive experiments conducted on various datasets. The results emphasize substantial enhancements in more than ten commonly assessed capabilities. Additionally, our model achieves state-of-the-art results across multiple widely recognized multimodal benchmarks.

Xinlong Wang, Xiaosong Zhang, Yue Cao et al.

We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formulated as an in-context coloring problem with random color mapping for each data sample. The objective is to accomplish diverse tasks according to the context, rather than relying on specific colors. After training, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text. SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation. Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively.

Hao Zhong, Muzhi Zhu, Shenyan Zeng et al.

Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for spatial reasoning in multimodal large language models (MLLMs) deployed in physical environments. However, current MLLMs lack systematic evaluation and training frameworks for these capabilities. We introduce ReasonMatch-Bench, a benchmark stratified by viewpoint displacement and matching granularity across indoor, outdoor, and object-centric scenarios, and show that current MLLMs still struggle with fine-grained wide-baseline correspondence: on a difficult 90-sample subset, human annotators achieve 84.0 F1, while the best existing baseline reaches 37.2. To bridge this gap, we build a scalable data-generation pipeline that automatically extracts wide-baseline view pairs from large-scale video-3D corpora, including RGB-D videos and SfM reconstructions, yielding diverse and verifiable supervision. We further propose Dynamic Correspondence Reinforcement Learning (DCRL), which combines Image-Level Viewpoint Progression and Point-Level Correspondence Curriculum to improve WBM training through verifiable rewards without explicit CoT supervision. Extensive experiments show that DCRL substantially improves ReasonMatch-Bench and transfers to related spatial benchmarks, while maintaining general visual understanding performance with modest gains on several benchmarks.

Peixian Chen, Mengdan Zhang, Yunhang Shen et al. · tencent-ai

Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with the price of bringing considerable computation burden for inference. More subtle usage is the DETR family, which eliminates the need for many hand-designed components in object detection but introduces a decoder demanding an extra-long time to converge. As a result, transformer-based object detection can not prevail in large-scale applications. To overcome these issues, we propose a novel decoder-free fully transformer-based (DFFT) object detector, achieving high efficiency in both training and inference stages, for the first time. We simplify objection detection into an encoder-only single-level anchor-based dense prediction problem by centering around two entry points: 1) Eliminate the training-inefficient decoder and leverage two strong encoders to preserve the accuracy of single-level feature map prediction; 2) Explore low-level semantic features for the detection task with limited computational resources. In particular, we design a novel lightweight detection-oriented transformer backbone that efficiently captures low-level features with rich semantics based on a well-conceived ablation study. Extensive experiments on the MS COCO benchmark demonstrate that DFFT_SMALL outperforms DETR by 2.5% AP with 28% computation cost reduction and more than $10$x fewer training epochs. Compared with the cutting-edge anchor-based detector RetinaNet, DFFT_SMALL obtains over 5.5% AP gain while cutting down 70% computation cost.

Chi Zhang, Wei Yin, Gang Yu et al. · deepmind, tencent-ai

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate for mix-dataset training, enhancing generalization across diverse scenes. However, such mixed dataset training yields depth predictions only up to an unknown scale and shift, hindering accurate 3D reconstructions. Existing solutions necessitate extra 3D datasets or geometry-complete depth annotations, constraints that limit their versatility. In this paper, we propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. To produce realistic 3D structures, we render novel views of the reconstructed scenes and design loss functions to promote depth estimation consistency across different views. Comprehensive experiments underscore our framework's superior generalization capabilities, surpassing existing state-of-the-art methods on several benchmark datasets without leveraging extra training information. Moreover, our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients using solely unlabeled images.

Bowen Zhang, Zhi Tian, Quan Tang et al.

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.

Xiaojie Chu, Yongtao Wang, Chunhua Shen et al.

The development of scene text recognition (STR) in the era of deep learning has been mainly focused on novel architectures of STR models. However, training protocol (i.e., settings of the hyper-parameters involved in the training of STR models), which plays an equally important role in successfully training a good STR model, is under-explored for scene text recognition. In this work, we attempt to improve the accuracy of existing STR models by searching for optimal training protocol. Specifically, we develop a training protocol search algorithm, based on a newly designed search space and an efficient search algorithm using evolutionary optimization and proxy tasks. Experimental results show that our searched training protocol can improve the recognition accuracy of mainstream STR models by 2.7%~3.9%. In particular, with the searched training protocol, TRBA-Net achieves 2.1% higher accuracy than the state-of-the-art STR model (i.e., EFIFSTR), while the inference speed is 2.3x and 3.7x faster on CPU and GPU respectively. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method and the generalization ability of the training protocol found by our search method. Code is available at https://github.com/VDIGPKU/STR_TPSearch.

Weijia Wu, Yuzhong Zhao, Mike Zheng Shou et al.

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model, which uses only text-image pairs during training. Our approach, called DiffuMask, exploits the potential of the cross-attention map between text and image, which is natural and seamless to extend the text-driven image synthesis to semantic mask generation. DiffuMask uses text-guided cross-attention information to localize class/word-specific regions, which are combined with practical techniques to create a novel high-resolution and class-discriminative pixel-wise mask. The methods help to reduce data collection and annotation costs obviously. Experiments demonstrate that the existing segmentation methods trained on synthetic data of DiffuMask can achieve a competitive performance over the counterpart of real data (VOC 2012, Cityscapes). For some classes (e.g., bird), DiffuMask presents promising performance, close to the stateof-the-art result of real data (within 3% mIoU gap). Moreover, in the open-vocabulary segmentation (zero-shot) setting, DiffuMask achieves a new SOTA result on Unseen class of VOC 2012. The project website can be found at https://weijiawu.github.io/DiffusionMask/.

Haoyi Zhu, Honghui Yang, Xiaoyang Wu et al.

In contrast to numerous NLP and 2D vision foundational models, learning a 3D foundational model poses considerably greater challenges. This is primarily due to the inherent data variability and diversity of downstream tasks. In this paper, we introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation, thereby establishing a pathway to 3D foundational models. Considering that informative 3D features should encode rich geometry and appearance cues that can be utilized to render realistic images, we propose to learn 3D representations by differentiable neural rendering. We train a 3D backbone with a devised volumetric neural renderer by comparing the rendered with the real images. Notably, our approach seamlessly integrates the learned 3D encoder into various downstream tasks. These tasks encompass not only high-level challenges such as 3D detection and segmentation but also low-level objectives like 3D reconstruction and image synthesis, spanning both indoor and outdoor scenarios. Besides, we also illustrate the capability of pre-training a 2D backbone using the proposed methodology, surpassing conventional pre-training methods by a large margin. For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness. Code and models are available at https://github.com/OpenGVLab/PonderV2.

Zhi Tian, Xiangxiang Chu, Xiaoming Wang et al.

We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant methods that use the bird-eye view (BEV), our proposed detector detects objects from the range view (RV, a.k.a. range image) of the LiDAR points. Due to the range view's compactness and compatibility with the LiDAR sensors' sampling process on self-driving cars, the range view-based object detector can be realized by solely exploiting the vanilla 2D convolutions, departing from the BEV-based methods which often involve complicated voxelization operations and sparse convolutions. For the first time, we show that an RV-based 3D detector with standard 2D convolutions alone can achieve comparable performance to state-of-the-art BEV-based detectors while being significantly faster and simpler. More importantly, almost all previous range view-based detectors only focus on single-frame point clouds, since it is challenging to fuse multi-frame point clouds into a single range view. In this work, we tackle this challenging issue with a novel range view projection mechanism, and for the first time demonstrate the benefits of fusing multi-frame point clouds for a range-view based detector. Extensive experiments on nuScenes show the superiority of our proposed method and we believe that our work can be strong evidence that an RV-based 3D detector can compare favourably with the current mainstream BEV-based detectors.

Shuai Jia, Bangjie Yin, Taiping Yao et al.

Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models. In this work, instead of performing perturbations on the low-level pixels, we propose to generate attacks through perturbing on the high-level semantics to improve attack transferability. Specifically, a unified flexible framework, Adversarial Attributes (Adv-Attribute), is designed to generate inconspicuous and transferable attacks on face recognition, which crafts the adversarial noise and adds it into different attributes based on the guidance of the difference in face recognition features from the target. Moreover, the importance-aware attribute selection and the multi-objective optimization strategy are introduced to further ensure the balance of stealthiness and attacking strength. Extensive experiments on the FFHQ and CelebA-HQ datasets show that the proposed Adv-Attribute method achieves the state-of-the-art attacking success rates while maintaining better visual effects against recent attack methods.

Bohan Zhuang, Jing Liu, Zizheng Pan et al.

Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by the efficient use of computation and memory resources. This survey provides the first systematic overview of the efficient training of Transformers, covering the recent progress in acceleration arithmetic and hardware, with a focus on the former. We analyze and compare methods that save computation and memory costs for intermediate tensors during training, together with techniques on hardware/algorithm co-design. We finally discuss challenges and promising areas for future research.

Kaining Ying, Qing Zhong, Weian Mao et al.

The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is directly supervised by the contrastive loss computed upon the contrastive items (CIs), which are sets of anchor/positive/negative embeddings. Recent online VIS methods leverage CIs sourced from one reference frame only, which we argue is insufficient for learning highly discriminative embeddings. Intuitively, a possible strategy to enhance CIs is replicating the inference phase during training. To this end, we propose a simple yet effective training strategy, called Consistent Training for Online VIS (CTVIS), which devotes to aligning the training and inference pipelines in terms of building CIs. Specifically, CTVIS constructs CIs by referring inference the momentum-averaged embedding and the memory bank storage mechanisms, and adding noise to the relevant embeddings. Such an extension allows a reliable comparison between embeddings of current instances and the stable representations of historical instances, thereby conferring an advantage in modeling VIS challenges such as occlusion, re-identification, and deformation. Empirically, CTVIS outstrips the SOTA VIS models by up to +5.0 points on three VIS benchmarks, including YTVIS19 (55.1% AP), YTVIS21 (50.1% AP) and OVIS (35.5% AP). Furthermore, we find that pseudo-videos transformed from images can train robust models surpassing fully-supervised ones.

Wenjia Wang, Yongtao Ge, Haiyi Mei et al.

As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body. The naive focal length assumptions can harm this task with the incorrectly formulated projection matrices. To solve this, we propose Zolly, the first 3DHMR method focusing on perspective-distorted images. Our approach begins with analysing the reason for perspective distortion, which we find is mainly caused by the relative location of the human body to the camera center. We propose a new camera model and a novel 2D representation, termed distortion image, which describes the 2D dense distortion scale of the human body. We then estimate the distance from distortion scale features rather than environment context features. Afterwards, we integrate the distortion feature with image features to reconstruct the body mesh. To formulate the correct projection matrix and locate the human body position, we simultaneously use perspective and weak-perspective projection loss. Since existing datasets could not handle this task, we propose the first synthetic dataset PDHuman and extend two real-world datasets tailored for this task, all containing perspective-distorted human images. Extensive experiments show that Zolly outperforms existing state-of-the-art methods on both perspective-distorted datasets and the standard benchmark (3DPW).

Chenhao Bai, Liqin Lu, Kaijun Wang et al.

Scaling robust robot policies requires more than broader randomization, because physical-domain experience must remain organized and learnable throughout training. We study when a policy can benefit from harder physics and identify recoverability as a central constraint in on-policy physical-domain scaling. In on-policy training, new dynamics are useful only insofar as they remain close enough to the current policy to generate corrective on-policy data, rather than collapsing rollouts into unrecoverable failures. Using quadruped locomotion as a physically demanding benchmark for embodied generalization, we introduce HORIZON, a checkpointed frontier curriculum that expands physical domains only within the current policy's recoverable boundary. HORIZON uses rollback and boundary refinement to govern each expansion step, turning fixed randomization into a continual process of physical-domain growth. Experiments reveal three regularities of physical-domain expansion. First, direct domain widening is uneven across physical axes and often unlearnable without staged ordering. Second, domain composition is non-monotonic, and adding more domains beyond a compact core can dilute recoverable joint samples and reduce overall robustness. Third, offline distillation of isolated experts cannot substitute for the joint interaction generated by on-policy curriculum. Together, these results frame physical-domain generalization as a continual growth problem for embodied control, with recoverability as the organizing principle for on-policy expansion.

Tong He, Wei Yin, Chunhua Shen et al.

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. In doing so it avoids the challenges that clustering-based methods face: introducing dependencies among different tasks of the model. We find the key to its success is assigning a suitable target to each sampled point. Instead of the commonly used static or distance-based assignment strategies, we propose to use an Optimal Transport approach to optimally assign target masks to the sampled points according to the dynamic matching costs. Our approach achieves promising results on both ScanNet and S3DIS benchmarks. The proposed approach removes intertask dependencies and thus represents a simpler and more flexible 3D instance segmentation framework than other competing methods, while achieving improved segmentation accuracy.

Yutong Xie, Jianpeng Zhang, Yong Xia et al.

Medical image benchmarks for the segmentation of organs and tumors suffer from the partially labeling issue due to its intensive cost of labor and expertise. Current mainstream approaches follow the practice of one network solving one task. With this pipeline, not only the performance is limited by the typically small dataset of a single task, but also the computation cost linearly increases with the number of tasks. To address this, we propose a Transformer based dynamic on-demand network (TransDoDNet) that learns to segment organs and tumors on multiple partially labeled datasets. Specifically, TransDoDNet has a hybrid backbone that is composed of the convolutional neural network and Transformer. A dynamic head enables the network to accomplish multiple segmentation tasks flexibly. Unlike existing approaches that fix kernels after training, the kernels in the dynamic head are generated adaptively by the Transformer, which employs the self-attention mechanism to model long-range organ-wise dependencies and decodes the organ embedding that can represent each organ. We create a large-scale partially labeled Multi-Organ and Tumor Segmentation benchmark, termed MOTS, and demonstrate the superior performance of our TransDoDNet over other competitors on seven organ and tumor segmentation tasks. This study also provides a general 3D medical image segmentation model, which has been pre-trained on the large-scale MOTS benchmark and has demonstrated advanced performance over BYOL, the current predominant self-supervised learning method. Code will be available at \url{https://git.io/DoDNet}.

Libo Sun, Wei Yin, Enze Xie et al.

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. It consists of two separate working modes to assist the localization and mapping. With a single monocular image input, the depth estimation module predicts a relative depth to help the localization module on improving the accuracy. With a sparse depth map and an RGB image input, the depth estimation module can generate accurate scale-consistent depth for dense mapping. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes. More significantly, our framework is able to boost the performances of existing geometry-based VO methods by a large margin.

Yongtao Ge, Qiang Zhou, Xinlong Wang et al.

Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we present Point-Teaching, a weakly semi-supervised object detection framework to fully exploit the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes.

Guangkai Xu, Wei Yin, Hao Chen et al.

3D scene reconstruction is a long-standing vision task. Existing approaches can be categorized into geometry-based and learning-based methods. The former leverages multi-view geometry but can face catastrophic failures due to the reliance on accurate pixel correspondence across views. The latter was proffered to mitigate these issues by learning 2D or 3D representation directly. However, without a large-scale video or 3D training data, it can hardly generalize to diverse real-world scenarios due to the presence of tens of millions or even billions of optimization parameters in the deep network. Recently, robust monocular depth estimation models trained with large-scale datasets have been proven to possess weak 3D geometry prior, but they are insufficient for reconstruction due to the unknown camera parameters, the affine-invariant property, and inter-frame inconsistency. Here, we propose a novel test-time optimization approach that can transfer the robustness of affine-invariant depth models such as LeReS to challenging diverse scenes while ensuring inter-frame consistency, with only dozens of parameters to optimize per video frame. Specifically, our approach involves freezing the pre-trained affine-invariant depth model's depth predictions, rectifying them by optimizing the unknown scale-shift values with a geometric consistency alignment module, and employing the resulting scale-consistent depth maps to robustly obtain camera poses and achieve dense scene reconstruction, even in low-texture regions. Experiments show that our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.

Xiang Wang, Shiwei Zhang, Haonan Qiu et al.

The field of controllable human-centric video generation has witnessed remarkable progress, particularly with the advent of diffusion models. However, achieving precise and localized control over human motion in videos, such as replacing or inserting individuals while preserving desired motion patterns, still remains a formidable challenge. In this work, we present the ReplaceAnyone framework, which focuses on localized human replacement and insertion featuring intricate backgrounds. Specifically, we formulate this task as an image-conditioned video inpainting paradigm with pose guidance, utilizing a unified end-to-end video diffusion architecture that facilitates image-conditioned video inpainting within masked regions. To prevent shape leakage and enable granular local control, we introduce diverse mask forms involving both regular and irregular shapes. Furthermore, we implement an enriched visual guidance mechanism to enhance appearance alignment, a hybrid inpainting encoder to further preserve the detailed background information in the masked video, and a two-phase optimization methodology to simplify the training difficulty. ReplaceAnyone enables seamless replacement or insertion of characters while maintaining the desired pose motion and reference appearance within a single framework. Extensive experimental results demonstrate the effectiveness of our method in generating realistic and coherent video content. The proposed ReplaceAnyone can be seamlessly applied not only to traditional 3D-UNet base models but also to DiT-based video models such as Wan2.1. The code will be available at https://github.com/ali-vilab/UniAnimate-DiT.

Yuling Xi, Hao Chen, Ning Wang et al.

Multi-task visual perception has a wide range of applications in scene understanding such as autonomous driving. In this work, we devise an efficient unified framework to solve multiple common perception tasks, including instance segmentation, semantic segmentation, monocular 3D detection, and depth estimation. Simply sharing the same visual feature representations for these tasks impairs the performance of tasks, while independent task-specific feature extractors lead to parameter redundancy and latency. Thus, we design two feature-merge branches to learn feature basis, which can be useful to, and thus shared by, multiple perception tasks. Then, each task takes the corresponding feature basis as the input of the prediction task head to fulfill a specific task. In particular, one feature merge branch is designed for instance-level recognition the other for dense predictions. To enhance inter-branch communication, the instance branch passes pixel-wise spatial information of each instance to the dense branch using efficient dynamic convolution weighting. Moreover, a simple but effective dynamic routing mechanism is proposed to isolate task-specific features and leverage common properties among tasks. Our proposed framework, termed D2BNet, demonstrates a unique approach to parameter-efficient predictions for multi-task perception. In addition, as tasks benefit from co-training with each other, our solution achieves on par results on partially labeled settings on nuScenes and outperforms previous works for 3D detection and depth estimation on the Cityscapes dataset with full supervision.

Zhen Yang, Ganggui Ding, Wen Wang et al.

By comparing the original and target prompts, we can obtain numerous editing pairs, each comprising an object and its corresponding editing target. To allow editability while maintaining fidelity to the input image, existing editing methods typically involve a fixed number of inversion steps that project the whole input image to its noisier latent representation, followed by a denoising process guided by the target prompt. However, we find that the optimal number of inversion steps for achieving ideal editing results varies significantly among different editing pairs, owing to varying editing difficulties. Therefore, the current literature, which relies on a fixed number of inversion steps, produces sub-optimal generation quality, especially when handling multiple editing pairs in a natural image. To this end, we propose a new image editing paradigm, dubbed Object-aware Inversion and Reassembly (OIR), to enable object-level fine-grained editing. Specifically, we design a new search metric, which determines the optimal inversion steps for each editing pair, by jointly considering the editability of the target and the fidelity of the non-editing region. We use our search metric to find the optimal inversion step for each editing pair when editing an image. We then edit these editing pairs separately to avoid concept mismatch. Subsequently, we propose an additional reassembly step to seamlessly integrate the respective editing results and the non-editing region to obtain the final edited image. To systematically evaluate the effectiveness of our method, we collect two datasets called OIRBench for benchmarking single- and multi-object editing, respectively. Experiments demonstrate that our method achieves superior performance in editing object shapes, colors, materials, categories, etc., especially in multi-object editing scenarios.

Haokui Zhang, Congyang Ou, Dawei Yan et al.

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or cross-modal visual-text similarity, which gives rise to certain limitations in compression performance and practical deployment. In contrast, we propose PIO-FVLM from the perspective of inference objectives, which transforms visual token compression into preserving output result invariance and selects tokens primarily by their importance to this goal. Specially, vision tokens are reordered with the guidance of token-level gradient saliency generated by our designed layer-local proxy loss, a coarse constraint from the current layer to the final result. Then the most valuable vision tokens are selected following the non-maximum suppression (NMS) principle. The proposed PIO-FVLM is training-free and compatible with FlashAttention, friendly to practical application and deployment. It can be deployed independently as an encoder-free method, or combined with encoder compression approaches like VisionZip for use as an encoder-involved method. On LLaVA-Next-7B, PIO-FVLM retains just 11.1% of visual tokens but maintains 97.2% of the original performance, with a 2.67$\times$ prefill speedup, 2.11$\times$ inference speedup, 6.22$\times$ lower FLOPs, and 6.05$\times$ reduced KV Cache overhead. Our code is available at https://github.com/ocy1/PIO-FVLM.

Canyu Zhao, Mingyu Liu, Wen Wang et al.

Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended periods, which is essential for long-form video production like movies. We propose MovieDreamer, a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering to pioneer long-duration video generation with intricate plot progressions and high visual fidelity. Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering. This method is akin to traditional movie production processes, where complex stories are factorized down into manageable scene capturing. Further, we employ a multimodal script that enriches scene descriptions with detailed character information and visual style, enhancing continuity and character identity across scenes. We present extensive experiments across various movie genres, demonstrating that our approach not only achieves superior visual and narrative quality but also effectively extends the duration of generated content significantly beyond current capabilities. Homepage: https://aim-uofa.github.io/MovieDreamer/.

Xiankang He, Peile Lin, Ying Cui et al.

Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative optimization techniques that struggle to mitigate the cumulative errors in multi-stage pipelines often lead to limited performance or high computational cost. In contrast, we propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms, thus enabling end-to-end feed-forward motion segmentation. Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion. Supported by recent advances in 4D scene geometry reconstruction (e.g., $π^3$), the proposed method leverages reliable camera poses and rich spatial-temporal priors, which ensure stable training and robust inference for the model. Extensive experiments demonstrate that by eliminating complex pre-processing and iterative refinement, our approach achieves state-of-the-art motion segmentation performance with high efficiency. The code is available at:https://github.com/zjutcvg/GeoMotion.