Hang Zhao

Tianyuan Zhang, Xuanyao Chen, Yue Wang et al.

Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently challenging due to depth estimation, visual occlusions, appearance ambiguity, etc. Moreover, objects are not consistently associated across time and cameras. To address that, we propose an end-to-end \textbf{MU}lti-camera \textbf{TR}acking framework called MUTR3D. In contrast to prior works, MUTR3D does not explicitly rely on the spatial and appearance similarity of objects. Instead, our method introduces \textit{3D track query} to model spatial and appearance coherent track for each object that appears in multiple cameras and multiple frames. We use camera transformations to link 3D trackers with their observations in 2D images. Each tracker is further refined according to the features that are obtained from camera images. MUTR3D uses a set-to-set loss to measure the difference between the predicted tracking results and the ground truths. Therefore, it does not require any post-processing such as non-maximum suppression and/or bounding box association. MUTR3D outperforms state-of-the-art methods by 5.3 AMOTA on the nuScenes dataset. Code is available at: \url{https://github.com/a1600012888/MUTR3D}.

Xiaoyu Tian, Tao Jiang, Longfei Yun et al.

Robotic perception requires the modeling of both 3D geometry and semantics. Existing methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details and struggling to handle general, out-of-vocabulary objects. 3D occupancy prediction, which estimates the detailed occupancy states and semantics of a scene, is an emerging task to overcome these limitations. To support 3D occupancy prediction, we develop a label generation pipeline that produces dense, visibility-aware labels for any given scene. This pipeline comprises three stages: voxel densification, occlusion reasoning, and image-guided voxel refinement. We establish two benchmarks, derived from the Waymo Open Dataset and the nuScenes Dataset, namely Occ3D-Waymo and Occ3D-nuScenes benchmarks. Furthermore, we provide an extensive analysis of the proposed dataset with various baseline models. Lastly, we propose a new model, dubbed Coarse-to-Fine Occupancy (CTF-Occ) network, which demonstrates superior performance on the Occ3D benchmarks. The code, data, and benchmarks are released at https://tsinghua-mars-lab.github.io/Occ3D/.

Jiageng Mao, Yuxi Qian, Junjie Ye et al.

We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs). The fundamental insight of our approach is the reformulation of motion planning as a language modeling problem, a perspective not previously explored. Specifically, we represent the planner inputs and outputs as language tokens, and leverage the LLM to generate driving trajectories through a language description of coordinate positions. Furthermore, we propose a novel prompting-reasoning-finetuning strategy to stimulate the numerical reasoning potential of the LLM. With this strategy, the LLM can describe highly precise trajectory coordinates and also its internal decision-making process in natural language. We evaluate our approach on the large-scale nuScenes dataset, and extensive experiments substantiate the effectiveness, generalization ability, and interpretability of our GPT-based motion planner. Code is now available at https://github.com/PointsCoder/GPT-Driver.

Zitian Tang, Wenjie Ye, Wei-Chiu Ma et al.

Inferring past human motion from RGB images is challenging due to the inherent uncertainty of the prediction problem. Thermal images, on the other hand, encode traces of past human-object interactions left in the environment via thermal radiation measurement. Based on this observation, we collect the first RGB-Thermal dataset for human motion analysis, dubbed Thermal-IM. Then we develop a three-stage neural network model for accurate past human pose estimation. Comprehensive experiments show that thermal cues significantly reduce the ambiguities of this task, and the proposed model achieves remarkable performance. The dataset is available at https://github.com/ZitianTang/Thermal-IM.

Xuanyao Chen, Tianyuan Zhang, Yue Wang et al.

Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics. Existing multi-modal 3D detection models usually involve customized designs depending on the sensor combinations or setups. In this work, we propose the first unified end-to-end sensor fusion framework for 3D detection, named FUTR3D, which can be used in (almost) any sensor configuration. FUTR3D employs a query-based Modality-Agnostic Feature Sampler (MAFS), together with a transformer decoder with a set-to-set loss for 3D detection, thus avoiding using late fusion heuristics and post-processing tricks. We validate the effectiveness of our framework on various combinations of cameras, low-resolution LiDARs, high-resolution LiDARs, and Radars. On NuScenes dataset, FUTR3D achieves better performance over specifically designed methods across different sensor combinations. Moreover, FUTR3D achieves great flexibility with different sensor configurations and enables low-cost autonomous driving. For example, only using a 4-beam LiDAR with cameras, FUTR3D (58.0 mAP) achieves on par performance with state-of-the-art 3D detection model CenterPoint (56.6 mAP) using a 32-beam LiDAR.

Tianyu Hua, Yonglong Tian, Sucheng Ren et al.

Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the effect various design choices have on the success of applying such training strategies for visual feature learning. Specifically, we introduce a novel strategy that we call Random Segments with Autoregressive Coding (RandSAC). In RandSAC, we group patch representations (image tokens) into hierarchically arranged segments; within each segment, tokens are predicted in parallel, similar to BERT, while across segment predictions are sequential, similar to GPT. We illustrate that randomized serialization of the segments significantly improves the performance and results in distribution over spatially-long (across-segments) and -short (within-segment) predictions which are effective for feature learning. We illustrate the pertinence of these design choices and explore alternatives on a number of datasets (e.g., CIFAR10, CIFAR100, ImageNet). While our pre-training strategy works with a vanilla Transformer, we also propose a conceptually simple, but highly effective, addition to the decoder that allows learnable skip-connections to encoder$'$s feature layers, which further improves the performance.

Junru Gu, Chenxu Hu, Tianyuan Zhang et al.

Perception and prediction are two separate modules in the existing autonomous driving systems. They interact with each other via hand-picked features such as agent bounding boxes and trajectories. Due to this separation, prediction, as a downstream module, only receives limited information from the perception module. To make matters worse, errors from the perception modules can propagate and accumulate, adversely affecting the prediction results. In this work, we propose ViP3D, a query-based visual trajectory prediction pipeline that exploits rich information from raw videos to directly predict future trajectories of agents in a scene. ViP3D employs sparse agent queries to detect, track, and predict throughout the pipeline, making it the first fully differentiable vision-based trajectory prediction approach. Instead of using historical feature maps and trajectories, useful information from previous timestamps is encoded in agent queries, which makes ViP3D a concise streaming prediction method. Furthermore, extensive experimental results on the nuScenes dataset show the strong vision-based prediction performance of ViP3D over traditional pipelines and previous end-to-end models.

Siwei Yang, Longlong Jing, Junfei Xiao et al.

The weakly supervised instance segmentation is a challenging task. The existing methods typically use bounding boxes as supervision and optimize the network with a regularization loss term such as pairwise color affinity loss for instance segmentation. Through systematic analysis, we found that the commonly used pairwise affinity loss has two limitations: (1) it works with color affinity but leads to inferior performance with other modalities such as depth gradient, (2)the original affinity loss does not prevent trivial predictions as intended but actually accelerates this process due to the affinity loss term being symmetric. To overcome these two limitations, in this paper, we propose a novel asymmetric affinity loss which provides the penalty against the trivial prediction and generalizes well with affinity loss from different modalities. With the proposed asymmetric affinity loss, our method outperforms the state-of-the-art methods on the Cityscapes dataset and outperforms our baseline method by 3.5% in mask AP.

Bowen Li, Ziyuan Huang, Junjie Ye et al.

Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world processing. Especially for unmanned aerial vehicles (UAVs), where robust tracking is more challenging and onboard computation is limited, the latency issue can be fatal. In this work, we present a simple framework for end-to-end latency-aware tracking, i.e., end-to-end predictive visual tracking (PVT++). Unlike existing solutions that naively append Kalman Filters after trackers, PVT++ can be jointly optimized, so that it takes not only motion information but can also leverage the rich visual knowledge in most pre-trained tracker models for robust prediction. Besides, to bridge the training-evaluation domain gap, we propose a relative motion factor, empowering PVT++ to generalize to the challenging and complex UAV tracking scenes. These careful designs have made the small-capacity lightweight PVT++ a widely effective solution. Additionally, this work presents an extended latency-aware evaluation benchmark for assessing an any-speed tracker in the online setting. Empirical results on a robotic platform from the aerial perspective show that PVT++ can achieve significant performance gain on various trackers and exhibit higher accuracy than prior solutions, largely mitigating the degradation brought by latency.

Longlong Jing, Ruichi Yu, Henrik Kretzschmar et al.

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

Simian Luo, Chuanhao Yan, Chenxu Hu et al.

The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semantically aligned features, then train an LDM with CAVP-aligned visual features on spectrogram latent space. The CAVP-aligned features enable LDM to capture the subtler audio-visual correlation via a cross-attention module. We further significantly improve sample quality with `double guidance'. Diff-Foley achieves state-of-the-art V2A performance on current large scale V2A dataset. Furthermore, we demonstrate Diff-Foley practical applicability and generalization capabilities via downstream finetuning. Project Page: see https://diff-foley.github.io/

Zhangchen Ye, Tao Jiang, Chenfeng Xu et al.

Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach that leverages temporal fusion through the geometric correspondence of voxels over time to improve the accuracy of 3D occupancy predictions. By sampling points along the line of sight of each voxel and integrating the features of these points from historical frames, we construct a cost volume feature map that refines current volume features for improved prediction outcomes. Our method takes advantage of parallax cues from historical observations and employs a data-driven approach to learn the cost volume. We validate the effectiveness of CVT-Occ through rigorous experiments on the Occ3D-Waymo dataset, where it outperforms state-of-the-art methods in 3D occupancy prediction with minimal additional computational cost. The code is released at \url{https://github.com/Tsinghua-MARS-Lab/CVT-Occ}.

Yiming Li, Ziang Cao, Andrew Liang et al.

We are interested in anticipating as early as possible the target location of a person's object manipulation action in a 3D workspace from egocentric vision. It is important in fields like human-robot collaboration, but has not yet received enough attention from vision and learning communities. To stimulate more research on this challenging egocentric vision task, we propose a large multimodality dataset of more than 1 million frames of RGB-D and IMU streams, and provide evaluation metrics based on our high-quality 2D and 3D labels from semi-automatic annotation. Meanwhile, we design baseline methods using recurrent neural networks and conduct various ablation studies to validate their effectiveness. Our results demonstrate that this new task is worthy of further study by researchers in robotics, vision, and learning communities.

Tingle Li, Yichen Liu, Andrew Owens et al.

From the patter of rain to the crunch of snow, the sounds we hear often convey the visual textures that appear within a scene. In this paper, we present a method for learning visual styles from unlabeled audio-visual data. Our model learns to manipulate the texture of a scene to match a sound, a problem we term audio-driven image stylization. Given a dataset of paired audio-visual data, we learn to modify input images such that, after manipulation, they are more likely to co-occur with a given input sound. In quantitative and qualitative evaluations, our sound-based model outperforms label-based approaches. We also show that audio can be an intuitive representation for manipulating images, as adjusting a sound's volume or mixing two sounds together results in predictable changes to visual style. Project webpage: https://tinglok.netlify.app/files/avstyle

Zihui Xue, Zhengqi Gao, Sucheng Ren et al.

Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide supervision signals to a student network learning from another modality. In contrast to the empirical success reported in prior works, the working mechanism of crossmodal KD remains a mystery. In this paper, we present a thorough understanding of crossmodal KD. We begin with two case studies and demonstrate that KD is not a universal cure in crossmodal knowledge transfer. We then present the modality Venn diagram to understand modality relationships and the modality focusing hypothesis revealing the decisive factor in the efficacy of crossmodal KD. Experimental results on 6 multimodal datasets help justify our hypothesis, diagnose failure cases, and point directions to improve crossmodal knowledge transfer in the future.

Yingwei Li, Tiffany Chen, Maya Kabkab et al.

Estimating the distance of objects is a safety-critical task for autonomous driving. Focusing on short-range objects, existing methods and datasets neglect the equally important long-range objects. In this paper, we introduce a challenging and under-explored task, which we refer to as Long-Range Distance Estimation, as well as two datasets to validate new methods developed for this task. We then proposeR4D, the first framework to accurately estimate the distance of long-range objects by using references with known distances in the scene. Drawing inspiration from human perception, R4D builds a graph by connecting a target object to all references. An edge in the graph encodes the relative distance information between a pair of target and reference objects. An attention module is then used to weigh the importance of reference objects and combine them into one target object distance prediction. Experiments on the two proposed datasets demonstrate the effectiveness and robustness of R4D by showing significant improvements compared to existing baselines. We are looking to make the proposed dataset, Waymo OpenDataset - Long-Range Labels, available publicly at waymo.com/open/download.

Lingyu Zhu, Esa Rahtu, Hang Zhao

This paper focuses on perceiving and navigating 3D environments using echoes and RGB image. In particular, we perform depth estimation by fusing RGB image with echoes, received from multiple orientations. Unlike previous works, we go beyond the field of view of the RGB and estimate dense depth maps for substantially larger parts of the environment. We show that the echoes provide holistic and in-expensive information about the 3D structures complementing the RGB image. Moreover, we study how echoes and the wide field-of-view depth maps can be utilised in robot navigation. We compare the proposed methods against recent baselines using two sets of challenging realistic 3D environments: Replica and Matterport3D. The implementation and pre-trained models will be made publicly available.

Zhengqi Gao, Sucheng Ren, Zihui Xue et al.

Multimodal fusion emerges as an appealing technique to improve model performances on many tasks. Nevertheless, the robustness of such fusion methods is rarely involved in the present literature. In this paper, we propose a training-free robust late-fusion method by exploiting conditional independence assumption and Jacobian regularization. Our key is to minimize the Frobenius norm of a Jacobian matrix, where the resulting optimization problem is relaxed to a tractable Sylvester equation. Furthermore, we provide a theoretical error bound of our method and some insights about the function of the extra modality. Several numerical experiments on AV-MNIST, RAVDESS, and VGGsound demonstrate the efficacy of our method under both adversarial attacks and random corruptions.

Xiong-Hui Chen, Junyin Ye, Hang Zhao et al.

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform various tasks directly through a few demonstrations of corresponding tasks, where the agent would meet many unexpected changes when deployed. In this scenario, the agent is expected to not only imitate the demonstration but also adapt to unforeseen environmental changes. This motivates us to propose a new topic called imitator learning (ItorL), which aims to derive an imitator module that can on-the-fly reconstruct the imitation policies based on very limited expert demonstrations for different unseen tasks, without any extra adjustment. In this work, we focus on imitator learning based on only one expert demonstration. To solve ItorL, we propose Demo-Attention Actor-Critic (DAAC), which integrates IL into a reinforcement-learning paradigm that can regularize policies' behaviors in unexpected situations. Besides, for autonomous imitation policy building, we design a demonstration-based attention architecture for imitator policy that can effectively output imitated actions by adaptively tracing the suitable states in demonstrations. We develop a new navigation benchmark and a robot environment for \topic~and show that DAAC~outperforms previous imitation methods \textit{with large margins} both on seen and unseen tasks.

Haohan Chi, Huan-ang Gao, Ziming Liu et al.

Vision-Language-Action (VLA) models for autonomous driving show promise but falter in unstructured corner case scenarios, largely due to a scarcity of targeted benchmarks. To address this, we introduce Impromptu VLA. Our core contribution is the Impromptu VLA Dataset: over 80,000 meticulously curated video clips, distilled from over 2M source clips sourced from 8 open-source large-scale datasets. This dataset is built upon our novel taxonomy of four challenging unstructured categories and features rich, planning-oriented question-answering annotations and action trajectories. Crucially, experiments demonstrate that VLAs trained with our dataset achieve substantial performance gains on established benchmarks--improving closed-loop NeuroNCAP scores and collision rates, and reaching near state-of-the-art L2 accuracy in open-loop nuScenes trajectory prediction. Furthermore, our Q&A suite serves as an effective diagnostic, revealing clear VLM improvements in perception, prediction, and planning. Our code, data and models are available at https://github.com/ahydchh/Impromptu-VLA.

Chenzhuang Du, Yue Zhao, Chonghua Liao et al.

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal models in certain tasks. It's clear that their incorporation into multi-modal learning would significantly improve performance. However, multi-modal learning with these models still suffers from insufficient learning of uni-modal features, which weakens the resulting multi-modal model's generalization ability. While fine-tuning uni-modal models separately and then aggregating their predictions is straightforward, it doesn't allow for adequate adaptation between modalities, also leading to sub-optimal results. To this end, we introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA). By freezing the weights of uni-modal fine-tuned models, adding extra trainable rank decomposition matrices to them, and subsequently performing multi-modal joint training, our method enhances adaptation between modalities and boosts overall performance. We demonstrate the effectiveness of MMLoRA on three dataset categories: audio-visual (e.g., AVE, Kinetics-Sound, CREMA-D), vision-language (e.g., MM-IMDB, UPMC Food101), and RGB-Optical Flow (UCF101).

Renhao Wang, Hang Zhao, Yang Gao

Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO. This gap exists largely because commonly used random crop augmentations obtain semantically inconsistent content in crowded scene images of diverse objects. Previous works use preprocessing pipelines to localize salient objects for improved cropping, but an end-to-end solution is still elusive. In this work, we propose a framework which accomplishes this goal via joint learning of representations and segmentation. We leverage segmentation masks to train a model with a mask-dependent contrastive loss, and use the partially trained model to bootstrap better masks. By iterating between these two components, we ground the contrastive updates in segmentation information, and simultaneously improve segmentation throughout pretraining. Experiments show our representations transfer robustly to downstream tasks in classification, detection and segmentation.

Yang Li, Zongzheng Zhang, Xuchong Qiu et al. · tsinghua

Understanding lane toplogy relationships accurately is critical for safe autonomous driving. However, existing two-stage methods suffer from inefficiencies due to error propagations and increased computational overheads. To address these challenges, we propose a one-stage architecture that simultaneously predicts traffic elements, lane centerlines and topology relationship, improving both the accuracy and inference speed of lane topology understanding for autonomous driving. Our key innovation lies in reusing intermediate attention resources within distinct transformer decoders. This approach effectively leverages the inherent relational knowledge within the element detection module to enable the modeling of topology relationships among traffic elements and lanes without requiring additional computationally expensive graph networks. Furthermore, we are the first to demonstrate that knowledge can be distilled from models that utilize standard definition (SD) maps to those operates without using SD maps, enabling superior performance even in the absence of SD maps. Extensive experiments on the OpenLane-V2 dataset show that our approach outperforms baseline methods in both accuracy and efficiency, achieving superior results in lane detection, traffic element identification, and topology reasoning. Our code is available at https://github.com/Yang-Li-2000/one-stage.git.

Zhuoguang Chen, Kenan Li, Xiuyu Yang et al.

Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial comprehensiveness or temporal consistency. In this work, we introduce a brand-new task, Camera-based 4D Panoptic Occupancy Tracking, which simultaneously addresses panoptic occupancy segmentation and object tracking from camera-only input. Furthermore, we propose TrackOcc, a cutting-edge approach that processes image inputs in a streaming, end-to-end manner with 4D panoptic queries to address the proposed task. Leveraging the localization-aware loss, TrackOcc enhances the accuracy of 4D panoptic occupancy tracking without bells and whistles. Experimental results demonstrate that our method achieves state-of-the-art performance on the Waymo dataset. The source code will be released at https://github.com/Tsinghua-MARS-Lab/TrackOcc.

Tianyuan Yuan, Yucheng Mao, Jiawei Yang et al.

Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in unfamiliar urban areas. Unlike these systems, humans do not solely depend on immediate observations to perceive the environment. In navigating new cities, humans gradually develop a preliminary mental map to supplement real-time perception during subsequent visits. Inspired by this human approach, we introduce a novel framework, PreSight, that leverages past traversals to construct static prior memories, enhancing online perception in later navigations. Our method involves optimizing a city-scale neural radiance field with data from previous journeys to generate neural priors. These priors, rich in semantic and geometric details, are derived without manual annotations and can seamlessly augment various state-of-the-art perception models, improving their efficacy with minimal additional computational cost. Experimental results on the nuScenes dataset demonstrate the framework's high compatibility with diverse online perception models. Specifically, it shows remarkable improvements in HD-map construction and occupancy prediction tasks, highlighting its potential as a new perception framework for autonomous driving systems. Our code will be released at https://github.com/yuantianyuan01/PreSight.

Anna Min, Chenxu Hu, Yi Ren et al.

Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automatic speech recognition (ASR) and machine translation (MT) models. In this paper, we explore the benefits of incorporating multiple candidates from ASR and self-supervised speech features into MT. Our analysis reveals that the primary cause of cascading errors stems from the increased divergence between similar samples in the speech domain when mapped to the text domain. By including multiple candidates and self-supervised speech features, our approach allows the machine translation model to choose the right words and ensure precise translation using various speech samples. This strategy minimizes error spread and takes advantage of large ASR and MT datasets, along with pre-trained ASR/MT models, while addressing associated issues.

Ruixun Liu, Lingyu Kong, Derun Li et al.

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified multimodal reasoning process. Unlike prior approaches that rely on explicit 3D inputs, OccVLA treats dense 3D occupancy as both a predictive output and a supervisory signal, enabling the model to learn fine-grained spatial structures directly from 2D visual inputs. The occupancy predictions are regarded as implicit reasoning processes and can be skipped during inference without performance degradation, thereby adding no extra computational overhead. OccVLA achieves state-of-the-art results on the nuScenes benchmark for trajectory planning and demonstrates superior performance on 3D visual question-answering tasks, offering a scalable, interpretable, and fully vision-based solution for autonomous driving.

Xiaoyu Tian, Haoxi Ran, Yue Wang et al.

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud representation learning framework, based on geometric feature reconstruction. In contrast to recent papers that directly adopt masked autoencoder (MAE) and only predict original coordinates or occupancy from masked point clouds, our method revisits differences between images and point clouds and identifies three self-supervised learning objectives peculiar to point clouds, namely centroid prediction, normal estimation, and curvature prediction. Combined with occupancy prediction, these four objectives yield an nontrivial self-supervised learning task and mutually facilitate models to better reason fine-grained geometry of point clouds. Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder; second, a lightweight Transformer decoder predicts centroid, normal, and curvature for points in each voxel. We transfer the pre-trained Transformer encoder to a downstream peception model. On the nuScene Datset, our model achieves 3.38 mAP improvment for object detection, 2.1 mIoU gain for segmentation, and 1.7 AMOTA gain for multi-object tracking. We also conduct experiments on the Waymo Open Dataset and achieve significant performance improvements over baselines as well.

Chenzhuang Du, Jiaye Teng, Tingle Li et al.

We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. Multi-modal models are expected to benefit from cross-modal interactions on the basis of ensuring uni-modal feature learning. However, recent supervised multi-modal late-fusion training approaches still suffer from insufficient learning of uni-modal features on each modality. We prove that this phenomenon does hurt the model's generalization ability. To this end, we propose to choose a targeted late-fusion learning method for the given supervised multi-modal task from Uni-Modal Ensemble(UME) and the proposed Uni-Modal Teacher(UMT), according to the distribution of uni-modal and paired features. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets, including VGG-Sound, Kinetics-400, UCF101, and ModelNet40.

Hang Zhao, Chen Zhang, Belei Zhu et al.

In this paper, we propose S3T, a self-supervised pre-training method with Swin Transformer for music classification, aiming to learn meaningful music representations from massive easily accessible unlabeled music data. S3T introduces a momentum-based paradigm, MoCo, with Swin Transformer as its feature extractor to music time-frequency domain. For better music representations learning, S3T contributes a music data augmentation pipeline and two specially designed pre-processors. To our knowledge, S3T is the first method combining the Swin Transformer with a self-supervised learning method for music classification. We evaluate S3T on music genre classification and music tagging tasks with linear classifiers trained on learned representations. Experimental results show that S3T outperforms the previous self-supervised method (CLMR) by 12.5 percents top-1 accuracy and 4.8 percents PR-AUC on two tasks respectively, and also surpasses the task-specific state-of-the-art supervised methods. Besides, S3T shows advances in label efficiency using only 10% labeled data exceeding CLMR on both tasks with 100% labeled data.

Zehui Chen, Zhenyu Li, Shiquan Zhang et al.

Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving. However, it remains challenging to make these two data sources complementary and beneficial to each other. In this paper, we propose \textit{AutoAlign}, an automatic feature fusion strategy for 3D object detection. Instead of establishing deterministic correspondence with camera projection matrix, we model the mapping relationship between the image and point clouds with a learnable alignment map. This map enables our model to automate the alignment of non-homogenous features in a dynamic and data-driven manner. Specifically, a cross-attention feature alignment module is devised to adaptively aggregate \textit{pixel-level} image features for each voxel. To enhance the semantic consistency during feature alignment, we also design a self-supervised cross-modal feature interaction module, through which the model can learn feature aggregation with \textit{instance-level} feature guidance. Extensive experimental results show that our approach can lead to 2.3 mAP and 7.0 mAP improvements on the KITTI and nuScenes datasets, respectively. Notably, our best model reaches 70.9 NDS on the nuScenes testing leaderboard, achieving competitive performance among various state-of-the-arts.

Qi Li, Yue Wang, Yilun Wang et al.

Constructing HD semantic maps is a central component of autonomous driving. However, traditional pipelines require a vast amount of human efforts and resources in annotating and maintaining the semantics in the map, which limits its scalability. In this paper, we introduce the problem of HD semantic map learning, which dynamically constructs the local semantics based on onboard sensor observations. Meanwhile, we introduce a semantic map learning method, dubbed HDMapNet. HDMapNet encodes image features from surrounding cameras and/or point clouds from LiDAR, and predicts vectorized map elements in the bird's-eye view. We benchmark HDMapNet on nuScenes dataset and show that in all settings, it performs better than baseline methods. Of note, our camera-LiDAR fusion-based HDMapNet outperforms existing methods by more than 50% in all metrics. In addition, we develop semantic-level and instance-level metrics to evaluate the map learning performance. Finally, we showcase our method is capable of predicting a locally consistent map. By introducing the method and metrics, we invite the community to study this novel map learning problem.

Yue Zhao, Chenzhuang Du, Hang Zhao et al.

In vision-based reinforcement learning (RL) tasks, it is prevalent to assign auxiliary tasks with a surrogate self-supervised loss so as to obtain more semantic representations and improve sample efficiency. However, abundant information in self-supervised auxiliary tasks has been disregarded, since the representation learning part and the decision-making part are separated. To sufficiently utilize information in auxiliary tasks, we present a simple yet effective idea to employ self-supervised loss as an intrinsic reward, called Intrinsically Motivated Self-Supervised learning in Reinforcement learning (IM-SSR). We formally show that the self-supervised loss can be decomposed as exploration for novel states and robustness improvement from nuisance elimination. IM-SSR can be effortlessly plugged into any reinforcement learning with self-supervised auxiliary objectives with nearly no additional cost. Combined with IM-SSR, the previous underlying algorithms achieve salient improvements on both sample efficiency and generalization in various vision-based robotics tasks from the DeepMind Control Suite, especially when the reward signal is sparse.

Hang Zhao, Chuang Gan, Andrew Rouditchenko et al.

We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel. Our approach capitalizes on the natural synchronization of the visual and audio modalities to learn models that jointly parse sounds and images, without requiring additional manual supervision. Experimental results on a newly collected MUSIC dataset show that our proposed Mix-and-Separate framework outperforms several baselines on source separation. Qualitative results suggest our model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources.