Xiaolong Wang 0004

VLDB 2026 Research / reviewers in the wild / expert

dblp:91/952-4 · DBLP profile ↗

← Back

124ranked-venue papers

14as first author

91since 2021 · last 2025

0000-0003-3150-778XORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 119 · 14 first-author · 89 since 2021Graphics, computer vision, multimedia, augmented reality and games · 65 · 12 first-author · 42 since 2021Systems, architecture and hardware · 15 · 15 since 2021

Year	Publication	Venue	Position
2025	One-Minute Video Generation with Test-Time Training abstract Transformers today still struggle to generate one-minute videos because self-attention layers are inefficient for long context. Alternatives such as Mamba layers struggle to produce coherent scenes because their hidden states are small and less expressive. We experiment with Test-Time Training (TTT) layers, whose hidden states themselves can be neural networks, therefore larger and more expressive. Adding TTT layers into a pre-trained Transformer enables it to generate one-minute videos from text storyboards. We curate a dataset based on Tom and Jerry cartoons as a proof-of-concept benchmark. Compared to baselines such as Mamba 2, Gated DeltaNet, and sliding-window attention layers, TTT layers generate much more coherent videos that tell complete stories, leading by 34 Elo points in a human evaluation of 100 videos per method. Although promising, our results are still limited in physical realism, and the efficiency of our implementation can be further improved.Sample videos, code and annotations are available at: https://test-time-training.github.io/video-dit Karan Dalal, Daniel Koceja, Yue Zhao 0006, Shihao Han, Ka Chun Cheung, Jan Kautz, Yejin Choi 0001, Yu Sun 0020, Xiaolong Wang 0004	CVPR	10
2025	EditAR: Unified Conditional Generation with Autoregressive Models abstract Recent progress in controllable image generation and editing is largely driven by diffusion-based methods. Although diffusion models perform exceptionally well in specific tasks with tailored designs, establishing a unified model is still challenging. In contrast, autoregressive models inherently feature a unified tokenized representation, which simplifies the creation of a single foundational model for various tasks. In this work, we propose EditAR, a single unified autoregressive framework for a variety of conditional image generation tasks, e.g., image editing, depth-to-image, edge-to-image, segmentation-to-image. The model takes both images and instructions as inputs, and predicts the edited images tokens in a vanilla next-token paradigm. To enhance the text-to-image alignment, we further propose to distill the knowledge from foundation models into the autoregressive modeling process. We evaluate its effectiveness across diverse tasks on established benchmarks, showing competitive performance to various state-of-the-art task-specific methods. Project page: https://jitengmu.github.io/EditAR/ Jiteng Mu, Nuno Vasconcelos, Xiaolong Wang 0004	CVPR	3
2025	Parallel Sequence Modeling via Generalized Spatial Propagation Network abstract We present the Generalized Spatial Propagation Network (GSPN), a new attention mechanism optimized for vision tasks that inherently captures 2D spatial structures. Existing attention models, including transformers, linear attention, and state-space models like Mamba, process multidimensional data as 1D sequences, compromising spatial coherence and efficiency. GSPN overcomes these limitations by directly operating on spatially coherent image data and forming dense pairwise connections through a line-scan approach. Central to GSPN is the Stability-Context Condition, which ensures stable, long-context propagation across 2D sequences and reduces the effective sequence length to $\sqrt N $ for a square map with N elements, which significantly enhances computational efficiency. With learnable, input-dependent weights and no reliance on positional embeddings, GSPN achieves superior spatial fidelity and state-of-the-art performance in vision tasks, including ImageNet classification, class-guided image generation, and text-to-image generation. Notably, GSPN accelerates SD-XL with softmax-attention by over 84× when generating 16K images. Project page: https://whj363636.github.io/GSPN/ Wonmin Byeon, Jinwei Gu, Ka Chun Cheung, Xiaolong Wang 0004, Kai Han 0001, Jan Kautz, Sifei Liu	CVPR	6
2025	Hierarchical World Models as Visual Whole-Body Humanoid Controllers abstract Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both of which are trained with rewards. Our approach produces highly performant control policies in 8 tasks with a simulated 56-DoF humanoid, while synthesizing motions that are broadly preferred by humans. Code and videos: https://www.nicklashansen.com/rlpuppeteer Nicklas Hansen 0001, Jyothir S. V, Vlad Sobal, Yann LeCun, Xiaolong Wang 0004, Hao Su 0001	ICLR	5
2025	Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes abstract Modern 3D engines and graphics pipelines require mesh as a memory-efficient representation, which allows efficient rendering, geometry processing, texture editing, and many other downstream operations. However, it is still highly difficult to obtain high-quality mesh in terms of detailed structure and time consistency from dynamic observations. To this end, we introduce Dynamic Gaussians Mesh (DG-Mesh), a framework to reconstruct a high-fidelity and time-consistent mesh from dynamic input. Our work leverages the recent advancement in 3D Gaussian Splatting to construct the mesh sequence with temporal consistency from dynamic observations. Building on top of this representation, DG-Mesh recovers high-quality meshes from the Gaussian points and can track the mesh vertices over time, which enables applications such as texture editing on dynamic objects. We introduce the Gaussian-Mesh Anchoring, which encourages evenly distributed Gaussians, resulting better mesh reconstruction through mesh-guided densification and pruning on the deformed Gaussians. By applying cycle-consistent deformation between the canonical and the deformed space, we can project the anchored Gaussian back to the canonical space and optimize Gaussians across all time frames. During the evaluation on different datasets, DG-Mesh provides significantly better mesh reconstruction and rendering than baselines. Isabella Liu, Hao Su 0001, Xiaolong Wang 0004	ICLR	3
2025	3D-Spatial Multimodal Memory abstract We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities, encompassing a wide range of knowledge. In our exploration, we identify two key challenges in previous works on feature splatting: (1) computational constraints in storing high-dimensional features for each Gaussian primitive, and (2) misalignment or information loss between distilled features and foundation model features. To address these challenges, we propose M3 with key components of principal scene components and Gaussian memory attention, enabling efficient training and inference. To validate M3, we conduct comprehensive quantitative evaluations of feature similarity and downstream tasks, as well as qualitative visualizations to highlight the pixel trace of Gaussian memory attention. Our approach encompasses a diverse range of foundation models, including vision-language models (VLMs), perception models, and large multimodal and language models (LMMs/LLMs). Furthermore, to demonstrate real-world applicability, we deploy M3’s feature field in indoor scenes on a quadruped robot. Notably, we claim that M3 is the first work to address the core compression challenges in 3D feature distillation. Xueyan Zou, Ri-Zhao Qiu, Xuanbin Peng, Jianglong Ye, Sifei Liu, Xiaolong Wang 0004	ICLR	7
2025	Learning to (Learn at Test Time): RNNs with Expressive Hidden States abstract Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expressive power of their hidden states. We present a practical framework for instantiating sequence modeling layers with linear complexity and expressive hidden states. The key idea is to make the hidden state a machine learning model itself, and the update rule a step of self-supervised learning. Since the hidden state is updated by training even on test sequences, our layers are called Test-Time Training (TTT) layers. We consider two instantiations: TTT-Linear and TTT-MLP, whose hidden state is a linear model and a two-layer MLP respectively. We evaluate our instantiations at the scale of 125M to 1.3B parameters, comparing with a strong Transformer and Mamba, a modern RNN. Similar to Transformer, TTT-Linear and TTT-MLP can keep reducing perplexity by conditioning on more tokens, while Mamba cannot after 16k context. TTT-MLP still faces challenges in memory I/O, but shows larger potential in long context, pointing to a promising direction for future research. Yu Sun 0020, Karan Dalal, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang 0004, Oluwasanmi Koyejo, Tatsunori B. Hashimoto, Carlos Guestrin	ICML	9
2025	HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots abstract Humanoid whole-body control requires adapting to diverse tasks such as navigation, loco-manipulation, and tabletop manipulation, each demanding a different mode of control. For example, navigation relies on root velocity or position tracking, while tabletop manipulation prioritizes upper-body joint angle tracking. Existing approaches typically train individual policies tailored to a specific command space, limiting their transferability across modes. We present the key insight that full-body kinematic motion imitation can serve as a common abstraction for all these tasks and provide general-purpose motor skills for learning multiple modes of whole-body control. Building on this, we propose HOVER (Humanoid Versatile Controller), a multi-mode policy distillation framework that consolidates diverse control modes into a unified policy. HOVER enables seamless transitions between control modes while preserving the distinct advantages of each, offering a robust and scalable solution for humanoid control across a wide range of modes. By eliminating the need for policy retraining for each control mode, our approach improves efficiency and flexibility for future humanoid applications. Tairan He, Toru Lin, Zhengyi Luo 0002, Zhenjia Xu, Zhenyu Jiang 0002, Jan Kautz, Changliu Liu, Guanya Shi, Xiaolong Wang 0004, Linxi Fan, Yuke Zhu	ICRA	10
2025	SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation abstract We introduce SPOT, an object-centric imitation learning framework. The key idea is to capture each task by an object-centric representation, specifically the SE(3) object pose trajectory relative to the target. This approach decouples embodiment actions from sensory inputs, facilitating learning from various demonstration types, including both action-based and action-less human hand demonstrations, as well as crossembodiment generalization. Additionally, object pose trajectories inherently capture planning constraints from demonstrations without the need for manually-crafted rules. To guide the robot in executing the task, the object trajectory is used to condition a diffusion policy. We systematically evaluate our method on simulation and real-world tasks. In real-world evaluation, using only eight demonstrations shot on an iPhone, our approach completed all tasks while fully complying with task constraints. Project page: https://nvlabs.github.io/object_centric_diffusion Cheng-Chun Hsu, Bowen Wen, Jie Xu 0028, Yashraj S. Narang, Xiaolong Wang 0004, Yuke Zhu, Joydeep Biswas, Stanley T. Birchfield	ICRA	5
2025	Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control abstract Humanoid robots require both robust lower-body locomotion and precise upper-body manipulation. While recent Reinforcement Learning (RL) approaches provide whole-body loco-manipulation policies, they lack precise manipulation with high DoF arms. In this paper, we propose decoupling upper-body control from locomotion, using inverse kinematics (IK) and motion retargeting for precise manipulation, while RL focuses on robust lower-body locomotion. We introduce PMP (Predictive Motion Priors), trained with Conditional Variational Autoencoder (CVAE) to effectively represent upper-body motions. The locomotion policy is trained conditioned on this upper-body motion representation, ensuring that the system re-mains robust with both manipulation and locomotion. We show that CVAE features are crucial for stability and robustness, and significantly outperforms RL-based whole-body control in precise manipulation. With precise upper-body motion and robust lower-body locomotion control, operators can remotely control the humanoid to walk around and explore different environments, while performing diverse manipulation tasks. Chenhao Lu, Xuxin Cheng, Jialong Li 0003, Mazeyu Ji, Chengjing Yuan, Sha Yi, Xiaolong Wang 0004	ICRA	9
2025	WildLMa: Long Horizon Loco-Manipulation in the Wild abstract ‘In-the-wild’ mobile manipulation aims to deploy robots in diverse real-world environments, which requires the robot to (1) have skills that generalize across object configurations; (2) be capable of long-horizon task execution in diverse environments; and (3) perform complex manipulation beyond pick-and-place. Quadruped robots with manipulators hold promise for extending the workspace and enabling robust locomotion, but existing results do not investigate such a capability. This paper proposes WildLMa with three components to address these issues: (1) adaptation of learned low-level controller for VR-enabled whole-body teleoperation and traversability; (2) WildLMa-Skill - a library of generalizable visuomotor skills acquired via imitation learning or heuristics and (3) WildLMa-Planner - an interface of learned skills that allow LLM planners to coordinate skills for long-horizon tasks. We demonstrate the importance of high-quality training data by achieving higher grasping success rate over existing RL baselines using only tens of demonstrations. WildLMa exploits CLIP for language-conditioned imitation learning that empirically generalizes to objects unseen in training demonstrations. Besides extensive quantitative evaluation, we qualitatively demonstrate practical robot applications, such as cleaning up trash in university hallways or outdoor terrains, operating articulated objects, and rearranging items on a bookshelf. Ri-Zhao Qiu, Xuanbin Peng, Sai Aneesh Suryadevara, Minghuan Liu, Mazeyu Ji, Chengzhe Jia, Ruihan Yang, Xueyan Zou, Xiaolong Wang 0004	ICRA	11
2025	Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning abstract Teleoperation is a crucial tool for collecting human demonstrations, but controlling robots with bimanual dexterous hands remains a challenge. Existing teleoperation systems struggle to handle the complexity of coordinating two hands for intricate manipulations. We introduce Bunny-VisionPro, a real-time bimanual dexterous teleoperation system that leverages a VR headset. Unlike previous vision-based teleoperation systems, we design novel low-cost devices to provide haptic feedback to the operator, enhancing immersion. Our system prioritizes safety by incorporating collision and singularity avoidance while maintaining real-time performance through innovative designs. Bunny-VisionPro outperforms prior systems on a standard task suite, achieving higher success rates and reduced task completion times. Moreover, the high-quality teleoperation demonstrations improve downstream imitation learning performance, leading to better generalizability. Notably, Bunny-VisionPro enables imitation learning with challenging multi-stage, long-horizon dexterous manipulation tasks, which have rarely been addressed in previous work. Our system’s ability to handle bimanual manipulations while prioritizing safety and real-time performance makes it a powerful tool for advancing dexterous manipulation and imitation learning. Our web page is available at https://dingry.github.io/projects/bunny_visionpro. Runyu Ding, Yuzhe Qin, Jiyue Zhu, Chengzhe Jia, Ruihan Yang, Xiaolong Wang 0004	IROS	8
2025	Learning Generalizable Feature Fields for Mobile Manipulation abstract An open problem in mobile manipulation is how to represent objects and scenes in a unified manner so that robots can use both for navigation and manipulation. The latter requires capturing intricate geometry while understanding fine-grained semantics, whereas the former involves capturing the complexity inherent at an expansive physical scale. In this work, we present GeFF (Generalizable Feature Fields), a scene-level generalizable neural feature field that acts as a unified representation for both navigation and manipulation that performs in real-time. To do so, we treat generative novel view synthesis as a pre-training task, and then align the resulting rich scene priors with natural language via CLIP feature distillation. We demonstrate the effectiveness of this approach by deploying GeFF on a quadrupedal robot equipped with a manipulator. We quantitatively evaluate GeFF’s ability for open-vocabulary object-/part-level manipulation and show that GeFF outperforms point-based baselines in runtime and storage-accuracy trade-offs, with qualitative examples of semantics-aware navigation and articulated object manipulation. Ri-Zhao Qiu, Yafei Hu, Jianglong Ye, Jiteng Mu, Ruihan Yang, Nikolay Atanasov 0001, Sebastian A. Scherer, Xiaolong Wang 0004	IROS	11
2025	Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models abstract Learning-Based methods have achieved strong performance for quadrupedal locomotion. However, several challenges prevent quadrupeds from learning helpful indoor skills that require interaction with environments and humans: lack of end-effectors for manipulation, limited semantic under-standing using only simulation data, and low traversability and reachability in indoor environments. We present a system for quadrupedal mobile manipulation in indoor environments. It uses a front-mounted gripper for object manipulation, a low-level controller trained in simulation using egocentric depth for agile skills like climbing and whole-body tilting, and pre-trained vision-language models (VLMs) with a third-person fisheye and an egocentric RGB camera for semantic understanding and command generation. We evaluate our system in two unseen environments without any real-world data collection or training. Our system can zero-shot generalize to these environments and complete tasks, like following user’s commands to fetch a randomly placed stuff toy after climbing over a queen-sized bed, with a 60% success rate. Zipeng Fu, Xuxin Cheng, Xiaolong Wang 0004, Chelsea Finn	IROS	4
2025	WorldModelBench: Judging Video Generation Models As World Models abstract Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous driving. However, current benchmarks fail to rigorously evaluate these claims, focusing only on general video quality, ignoring important factors to world models such as physics adherence.To bridge this gap, we propose WorldModelBench, a benchmark designed to evaluate the world modeling capabilities of video generation models in application-driven domains. WorldModelBench offers two key advantages: (1) Against to nuanced world modeling violations: By incorporating instruction-following and physics-adherence dimensions, WorldModelBench detects subtle violations, such as irregular changes in object size that breach the mass conservation law—issues overlooked by prior benchmarks. (2) Aligned with large-scale human preferences: We crowd-source 67K human labels to accurately measure 14 frontier models. Using our high-quality human labels, we further fine-tune an accurate judger to automate the evaluation procedure, achieving 9.9% lower error in predicting world modeling violations than GPT-4o with 2B parameters. In addition, we demonstrate that training to align human annotations by maximizing the rewards from the judger noticeably improve the world modeling capability. The dataset is hosted in HuggingFace at https://huggingface.co/datasets/Efficient-Large-Model/worldmodelbench. The code to run evaluation is available at https://github.com/WorldModelBench-Team/WorldModelBench. Dacheng Li, Yunhao Fang, Yukang Chen, Shuo Yang 0011, Shiyi Cao, Justin Wong, Michael Luo, Xiaolong Wang 0004, Hongxu Yin, Joseph Gonzalez 0001, Ion Stoica, Song Han 0003, Yao Lu 0006	NeurIPS	8
2025	Test-Time Training on Video Streams abstract Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is first trained on the same instance using a self-supervised task such as reconstruction. We extend TTT to the streaming setting, where multiple test instances - video frames in our case - arrive in temporal order. Our extension is online TTT: The current model is initialized from the previous model, then trained on the current frame and a small window of frames immediately before. Online TTT significantly outperforms the fixed-model baseline for four tasks, on three real-world datasets. The improvements are more than 2.2x and 1.5x for instance and panoptic segmentation. Surprisingly, online TTT also outperforms its offline variant that accesses strictly more information, training on all frames from the entire test video regardless of temporal order. This finding challenges those in prior work using synthetic videos. We formalize a notion of locality as the advantage of online over offline TTT, and analyze its role with ablations and a theory based on bias-variance trade-off. Renhao Wang, Yu Sun 0020, Arnuv Tandon, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang 0004	J. Mach. Learn. Res.	7
2025	RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets abstract We present RigAnything , a novel autoregressive transformer-based model, which makes 3D assets rig-ready by probabilistically generating joints and skeleton topologies and assigning skinning weights in a template-free manner. Unlike most existing auto-rigging methods, which rely on predefined skeleton templates and are limited to specific categories like humanoid, RigAnything approaches the rigging problem in an autoregressive manner, iteratively predicting the next joint based on the global input shape and the previous prediction. While autoregressive models are typically used to generate sequential data, RigAnything extends its application to effectively learn and represent skeletons, which are inherently tree structures. To achieve this, we organize the joints in a breadth-first search (BFS) order, enabling the skeleton to be defined as a sequence of 3D locations and the parent index. Furthermore, our model improves the accuracy of position prediction by leveraging diffusion modeling, ensuring precise and consistent placement of joints within the hierarchy. This formulation allows the autoregressive model to efficiently capture both spatial and hierarchical relationships within the skeleton. Trained end-to-end on both RigNet and Objaverse datasets, RigAnything demonstrates state-of-the-art performance across diverse object types, including humanoids, quadrupeds, marine creatures, insects, and many more, surpassing prior methods in quality, robustness, generalizability, and efficiency. It achieves significantly faster performance than existing auto-rigging methods, completing rigging in under a few seconds per shape. Isabella Liu, Wang Yifan 0001, Hao Tan 0002, Zexiang Xu, Xiaolong Wang 0004, Hao Su 0001, Zifan Shi	ACM Trans. Graph.	6
2024	ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation abstract We propose a new dataset and a novel approach to learning hand-object interaction priors for hand and articulated object pose estimation. We first collect a dataset using visual teleoperation, where the human operator can directly play within a physical simulator to manipulate the articulated objects. We record the data and obtain free and accurate annotations on object poses and contact information from the simulator. Our system only requires an iPhone to record human hand motion, which can be easily scaled up and largely lower the costs of data and annotation collection. With this data, we learn 3D interaction priors including a discriminator (in a GAN) capturing the distribution of how object parts are arranged, and a diffusion model which generates the contact regions on articulated objects, guiding the hand pose estimation. Such structural and contact priors can easily transfer to real-world data with barely any domain gap. By using our data and learned priors, our method significantly improves the performance on joint hand and articulated object poses estimation over the existing state-of-the-art methods. The project is available at https://zehaozhu.github.io/ContactArt/. Zehao Zhu, Jiashun Wang, Yuzhe Qin, Deqing Sun, Varun Jampani, Xiaolong Wang 0004	3DV	6
2024	Image Neural Field Diffusion Models abstract Diffusion models have shown an impressive ability to model complex data distributions, with several key advantages over GANs, such as stable training, better coverage of the training distribution's modes, and the ability to solve inverse problems without extra training. However, most diffusion models learn the distribution of fixed-resolution images. We propose to learn the distribution of continuous images by training diffusion models on image neural fields, which can be rendered at any resolution, and show its advantages over fixed-resolution models. To achieve this, a key challenge is to obtain a latent space that represents photorealistic image neural fields. We propose a simple and effective method, inspired by several recent techniques but with key changes to make the image neural fields photo-realistic. Our method can be used to convert existing latent diffusion autoencoders into image neural field autoen-coders. We show that image neural field diffusion models can be trained using mixed-resolution image datasets, outperform fixed-resolution diffusion models followed by super-resolution models, and can solve inverse problems with conditions applied at different scales efficiently. Yinbo Chen, Oliver Wang, Richard Zhang 0001, Eli Shechtman, Xiaolong Wang 0004, Michaël Gharbi	CVPR	5
2024	COLMAP-Free 3D Gaussian Splatting abstract While neural rendering has led to impressive advances in scene reconstruction and novel view synthesis, it relies heavily on accurately pre-computed camera poses. To relax this constraint, multiple efforts have been made to train Neural Radiance Fields (NeRFs) without pre-processed camera poses. However, the implicit representations of NeRFs provide extra challenges to optimize the 3D structure and camera poses at the same time. On the other hand, the recently proposed 3D Gaussian Splatting provides new opportunities given its explicit point cloud representations. This paper leverages both the explicit geometric representation and the continuity of the input video stream to perform novel view synthesis without any SfM preprocessing. We process the input frames in a sequential manner and progressively grow the 3D Gaussians set by taking one input frame at a time, without the need to pre-compute the camera poses. Our method significantly improves over previous approaches in view synthesis and camera pose estimation under large motion changes. Our project page is https://oasisyang.github.io/colmap-free-3dgs. Xiaolong Wang 0004, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A. Efros	CVPR	2
2024	CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation abstract We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates across various tasks and exhibits generalizability with previously unseen objects. For example, it can rotate novel tetra-valve and penta-valve, despite human demonstrations only involving tri-valves. Our research demonstrates the significant potential of simulated human demonstrations for realworld dexterous manipulation tasks. More details can be found at https://cyber-demo.github.io/ Yuzhe Qin, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su 0001, Xiaolong Wang 0004	CVPR	7
2024	RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos abstract We introduce a new RGB-D object dataset captured in the wild called WildRGB-D. Unlike most existing real-world object-centric datasets which only come with RGB capturing, the direct capture of the depth channel allows better 3D annotations and broader downstream applications. WildRGB-D comprises large-scale category-level RGB-D object videos, which are taken using an iPhone to go around the objects in 360 degrees. It contains around 8500 recorded objects and nearly 20000 RGB-D videos across 46 common object categories. These videos are taken with diverse cluttered backgrounds with three setups to cover as many real-world scenarios as possible: (i) a single object in one video; (ii) multiple objects in one video; and (iii) an object with a static hand in one video. The dataset is annotated with object masks, real-world scale camera poses, and reconstructed aggregated point clouds from RGBD videos. We benchmark four tasks with WildRGB-D including novel view synthesis, camera pose estimation, object 6d pose estimation, and object surface reconstruction. Our experiments show that the large-scale capture of RGB-D objects provides a large potential to advance 3D object learning. Our project page is https://wildrgbd.github.io/. Hongchi Xia, Sifei Liu, Xiaolong Wang 0004	CVPR	4
2024	Pixel Aligned Language Models abstract Large language models have achieved great success in recent years, so as their variants in vision. Existing vision-language models can describe images in natural languages, answer visual-related questions, or perform complex reasoning about the image. However, it is yet unclear how localization tasks, such as word grounding or referring localization, can be performed using large language models. In this work, we aim to develop a vision-language model that can take locations, for example, a set of points or boxes, as either inputs or outputs. When taking locations as inputs, the model performs location-conditioned captioning, which generates captions for the indicated object or region. When generating locations as outputs, our model regresses pixel coordinates for each output word generated by the language model, and thus performs dense word grounding. Our model is pre-trained on the Localized Narrative dataset, which contains pixel-word-aligned captioning from human attention. We show our model can be applied to various location-aware vision-language tasks, including referring localization, location-conditioned captioning, and dense object captioning, archiving state-of-the-art performance on RefCOCO and Visual Genome. Xingyi Zhou, Shen Yan 0008, Xiuye Gu, Anurag Arnab, Chen Sun 0002, Xiaolong Wang 0004, Cordelia Schmid	CVPR	7
2024	HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data abstract 3D hand-object interaction data is scarce due to the hardware constraints in scaling up the data collection pro-cess. In this paper, we propose HOIDiffusion for generating realistic and diverse 3D hand-object interaction data. Our model is a conditional diffusion model that takes both the 3D hand-object geometric structure and text description as inputs for image synthesis. This offers a more control-lable and realistic synthesis as we can specify the structure and style inputs in a disentangled manner. HOIDiffusion is trained by leveraging a diffusion model pre-trained on large-scale natural images and a few 3D human demonstrations. Beyond controllable image synthesis, we adopt the generated 3D data for learning 6D object pose estimation and show its effectiveness in improving perception systems. Project page: https://mq-zhang1.github.io/HOIDiffusion. Zheng Ding, Sifei Liu, Zhuowen Tu, Xiaolong Wang 0004	CVPR	6
2024	Editable Image Elements for Controllable Synthesis Jiteng Mu, Michaël Gharbi, Richard Zhang 0001, Eli Shechtman, Nuno Vasconcelos, Xiaolong Wang 0004, Taesung Park	ECCV (2)	6
2024	Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting Ri-Zhao Qiu, Weijia Zeng, Xiaolong Wang 0004	ECCV (41)	4
2024	TD-MPC2: Scalable, Robust World Models for Continuous Control abstract TD-MPC is a model-based reinforcement learning (RL) algorithm that performs local trajectory optimization in the latent space of a learned implicit (decoder-free) world model. In this work, we present TD-MPC2: a series of improvements upon the TD-MPC algorithm. We demonstrate that TD-MPC2 improves significantly over baselines across 104 online RL tasks spanning 4 diverse task domains, achieving consistently strong results with a single set of hyperparameters. We further show that agent capabilities increase with model and data size, and successfully train a single 317M parameter agent to perform 80 tasks across multiple task domains, embodiments, and action spaces. We conclude with an account of lessons, opportunities, and risks associated with large TD-MPC2 agents. Explore videos, models, data, code, and more at https://tdmpc2.com Nicklas Hansen 0001, Hao Su 0001, Xiaolong Wang 0004	ICLR	3
2024	TUVF: Learning Generalizable Texture UV Radiance Fields abstract Textures are a vital aspect of creating visually appealing and realistic 3D models. In this paper, we study the problem of generating high-fidelity texture given shapes of 3D assets, which has been relatively less explored compared with generic 3D shape modeling. Our goal is to facilitate a controllable texture generation process, such that one texture code can correspond to a particular appearance style independent of any input shapes from a category. We introduce Texture UV Radiance Fields (TUVF) that generate textures in a learnable UV sphere space rather than directly on the 3D shape. This allows the texture to be disentangled from the underlying shape and transferable to other shapes that share the same UV space, i.e., from the same category. We integrate the UV sphere space with the radiance field, which provides a more efficient and accurate representation of textures than traditional texture maps. We perform our experiments on synthetic and real-world object datasets where we achieve not only realistic synthesis but also substantial improvements over state-of-the-arts on texture controlling and editing. An-Chieh Cheng, Sifei Liu, Xiaolong Wang 0004	ICLR	4
2024	3D Reconstruction with Generalizable Neural Fields using Scene Priors abstract High-fidelity 3D scene reconstruction has been substantially advanced by recent progress in neural fields. However, most existing methods train a separate network from scratch for each individual scene. This is not scalable, inefficient, and unable to yield good results given limited views. While learning-based multi-view stereo methods alleviate this issue to some extent, their multi-view setting makes it less flexible to scale up and to broad applications. Instead, we introduce training generalizable Neural Fields incorporating scene Priors (NFPs). The NFP network maps any single-view RGB-D image into signed distance and radiance values. A complete scene can be reconstructed by merging individual frames in the volumetric space WITHOUT a fusion module, which provides better flexibility. The scene priors can be trained on large-scale datasets, allowing for fast adaptation to the reconstruction of a new scene with fewer views. NFP not only demonstrates SOTA scene reconstruction performance and efficiency, but it also supports single-image novel-view synthesis, which is under-explored in neural fields. More qualitative results are available at: https://oasisyang.github.io/neural-prior. Shalini De Mello, Amey Kulkarni, Jan Kautz, Xiaolong Wang 0004, Sifei Liu	ICLR	6
2024	GenSim: Generating Robotic Simulation Tasks via Large Language Models abstract Collecting large amounts of real-world interaction data to train general robotic policies is often prohibitively expensive, thus motivating the use of simulation data. However, existing methods for data generation have generally focused on scene-level diversity (e.g., object instances and poses) rather than task-level diversity, due to the human effort required to come up with and verify novel tasks. This has made it challenging for policies trained on simulation data to demonstrate significant task-level generalization. In this paper, we propose to automatically generate rich simulation environments and expert demonstrations by exploiting a large language models' (LLM) grounding and coding ability. Our approach, dubbed GenSim, has two modes: goal-directed generation, wherein a target task is given to the LLM and the LLM proposes a task curriculum to solve the target task, and exploratory generation, wherein the LLM bootstraps from previous tasks and iteratively proposes novel tasks that would be helpful in solving more complex tasks. We use GPT4 to expand the existing benchmark by ten times to over 100 tasks, on which we conduct supervised finetuning and evaluate several LLMs including finetuned GPTs and Code Llama on code generation for robotic simulation tasks. Furthermore, we observe that LLMs-generated simulation programs can enhance task-level generalization significantly when used for multitask policy training. We further find that with minimal sim-to-real adaptation, the multitask policies pretrained on GPT4-generated simulation tasks exhibit stronger transfer to unseen long-horizon tasks in the real world and outperform baselines by 25%. See our project website (https://gen-sim.github.io) and demo (https://huggingface.co/spaces/Gen-Sim/Gen-Sim) for visualizations and open-source models and datasets. Lirui Wang, Yiyang Ling, Zhecheng Yuan, Mohit Shridhar, Chen Bao, Yuzhe Qin, Bailin Wang, Huazhe Xu, Xiaolong Wang 0004	ICLR	9
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	246
2024	Sim2Real Manipulation on Unknown Objects with Tactile-based Reinforcement Learning abstract Using tactile sensors for manipulation remains one of the most challenging problems in robotics. At the heart of these challenges is generalization: How can we train a tactile-based policy that can manipulate unseen and diverse objects? In this paper, we propose to perform Reinforcement Learning with only visual tactile sensing inputs on diverse objects in a physical simulator. By training with diverse objects in simulation, it enables the policy to generalize to unseen objects. However, leveraging simulation introduces the Sim2Real transfer problem. To mitigate this problem, we study different tactile representations and evaluate how each affects real-robot manipulation results after transfer. We conduct our experiments on diverse real-world objects and show significant improvements over baselines. Our project page is available at https://tactilerl.github.io/. Entong Su, Chengzhe Jia, Yuzhe Qin, Wenxuan Zhou 0001, Annabella Macaluso, Binghao Huang, Xiaolong Wang 0004	ICRA	7
2024	Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing abstract Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual feedback. However, the distinct nature of these modalities poses significant challenges. In this paper, we introduce a system that leverages visual and tactile sensory inputs to enable dexterous in-hand manipulation. Specifically, we propose Robot Synesthesia, a novel point cloudbased tactile representation inspired by human tactile-visual synesthesia. This approach allows for the simultaneous and seamless integration of both sensory inputs, offering richer spatial information and facilitating better reasoning about robot actions. Comprehensive ablations are performed on how the integration of vision and touch can improve reinforcement learning and Sim2Real performance. Our project page is available at https://yingyuan0414.github.io/visuotactile/. Haichuan Che, Yuzhe Qin, Binghao Huang, Zhao-Heng Yin, Kang-Won Lee 0001, Yi Wu 0013, Soo-Chul Lim, Xiaolong Wang 0004	ICRA	9
2024	Harmonic Mobile Manipulation abstract Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. Ruihan Yang, Yejin Kim 0003, Rose Hendrix, Aniruddha Kembhavi, Xiaolong Wang 0004, Kiana Ehsani	IROS	5
2024	SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models abstract Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs’ spatial perception and reasoning capabilities. SpatialRGPT advances VLMs’ spatial understanding through two key innovations: (i) a data curation pipeline that enables effective learning of regional representation from 3D scene graphs, and (ii) a flexible ``plugin'' module for integrating depth information into the visual encoder of existing VLMs. During inference, when provided with user-specified region proposals, SpatialRGPT can accurately perceive their relative directions and distances. Additionally, we propose SpatialRGBT-Bench, a benchmark with ground-truth 3D annotations encompassing indoor, outdoor, and simulated environments, for evaluating 3D spatial cognition in Vision-Language Models (VLMs). Our results demonstrate that SpatialRGPT significantly enhances performance in spatial reasoning tasks, both with and without local region prompts. The model also exhibits strong generalization capabilities, effectively reasoning about complex spatial relations and functioning as a region-aware dense reward annotator for robotic tasks. Code, dataset, and benchmark are released at https://www.anjiecheng.me/SpatialRGPT. An-Chieh Cheng, Hongxu Yin, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang 0004, Sifei Liu	NeurIPS	7
2024	A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data abstract Despite the availability of international prize-money competitions, scaled vehicles, and simulation environments, research on autonomous racing and the control of sports cars operating close to the limit of handling has been limited by the high costs of vehicle acquisition and management, as well as the limited physics accuracy of open-source simulators. In this paper, we propose a racing simulation platform based on the simulator Assetto Corsa to test, validate, and benchmark autonomous driving algorithms, including reinforcement learning (RL) and classical Model Predictive Control (MPC), in realistic and challenging scenarios. Our contributions include the development of this simulation platform, several state-of-the-art algorithms tailored to the racing environment, and a comprehensive dataset collected from human drivers. Additionally, we evaluate algorithms in the offline RL setting. All the necessary code (including environment and benchmarks), working examples, and datasets are publicly released and can be found at: https://github.com/dasGringuen/assettocorsagym. Adrian Remonda, Nicklas Hansen 0001, Ayoub Raji, Nicola Musiu, Marko Bertogna, Eduardo E. Veas, Xiaolong Wang 0004	NeurIPS	7
2023	DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects abstract To enable general-purpose robots, we will require the robot to operate daily articulated objects as humans do. Current robot manipulation has heavily relied on using a parallel gripper, which restricts the robot to a limited set of objects. On the other hand, operating with a multi-finger robot hand will allow better approximation to human behavior and enable the robot to operate on diverse articulated objects. To this end, we propose a new benchmark called DexArt, which involves Dexterous manipulation with Articulated objects in a physical simulator. In our benchmark, we define multiple complex manipulation tasks, and the robot hand will need to manipulate diverse articulated objects within each task. Our main focus is to evaluate the generalizability of the learned policy on unseen articulated objects. This is very challenging given the high degrees of freedom of both hands and objects. We use Reinforcement Learning with 3D representation learning to achieve generalization. Through extensive studies, we provide new insights into how 3D representation learning affects decision making in RL with 3D point cloud inputs. More details can be found at https://www.chenbao.tech/dexart/. Chen Bao, Helin Xu, Yuzhe Qin, Xiaolong Wang 0004	CVPR	4
2023	Policy Adaptation from Foundation Model Feedback abstract Recent progress on vision-language foundation models have brought significant advancement to building generalpurpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects and tasks. While this is encouraging, the policy still fails in most cases given an unseen task or environment. In this work, we propose Policy Adaptation from Foundation model Feedback (PAFF). When deploying the trained policy to a new task or a new environment, we first let the policy play with randomly generated instructions to record the demonstrations. While the execution could be wrong, we can use the pre-trained foundation models to provide feedback to relabel the demonstrations. This automatically provides new pairs of demonstration-instruction data for policy fine-tuning. We evaluate our method on a broad range of experiments with the focus on generalization on unseen objects, unseen tasks, unseen environments, and sim-to-real transfer. We show PAFF improves baselines by a large margin in all cases. Yuying Ge, Annabella Macaluso, Li Erran Li, Ping Luo 0002, Xiaolong Wang 0004	CVPR	5
2023	Zero-shot Pose Transfer for Unrigged Stylized 3D Characters abstract Transferring the pose of a reference avatar to stylized 3D characters of various shapes is a fundamental task in computer graphics. Existing methods either require the stylized characters to be rigged, or they use the stylized character in the desired pose as ground truth at training. We present a zero-shot approach that requires only the widely available deformed non-stylized avatars in training, and deforms stylized characters of significantly different shapes at inference. Classical methods achieve strong generalization by deforming the mesh at the triangle level, but this requires labelled correspondences. We leverage the power of local deformation, but without requiring explicit correspondence labels. We introduce a semi-supervised shape-understanding module to bypass the need for explicit correspondences at test time, and an implicit pose deformation module that deforms individual surface points to match the target pose. Further-more, to encourage realistic and accurate deformation of stylized characters, we introduce an efficient volume-based test-time training procedure. Because it does not need rigging, nor the deformed stylized character at training time, our model generalizes to categories with scarce annotation, such as stylized quadrupeds. Extensive experiments demonstrate the effectiveness of the proposed method compared to the state-of-the-art approaches trained with comparable or more supervision. Our project page is available at https://jiashunwang.github.io/ZPT/ Jiashun Wang, Sifei Liu, Shalini De Mello, Orazio Gallo, Xiaolong Wang 0004, Jan Kautz	CVPR	6
2023	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models abstract We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation. Text-to-image diffusion models have the remarkable ability to generate high-quality images with diverse open-vocabulary language descriptions. This demonstrates that their internal representation space is highly correlated with open concepts in the real world. Text-image discriminative models like CLIP, on the other hand, are good at classifying images into open-vocabulary labels. We leverage the frozen internal representations of both these models to perform panoptic segmentation of any category in the wild. Our approach outperforms the previous state of the art by significant margins on both open-vocabulary panoptic and semantic segmentation tasks. In particular, with COCO training only, our method achieves 23.4 PQ and 30.0 mIoU on the ADE20K dataset, with 8.3 PQ and 7.9 mIoU absolute improvement over the previous state of the art. We open-source our code and models at https://github.com/NVlabs/ODISE. Sifei Liu, Arash Vahdat, Wonmin Byeon, Xiaolong Wang 0004, Shalini De Mello	CVPR	5
2023	Neural Volumetric Memory for Visual Locomotion Control abstract Legged robots have the potential to expand the reach of autonomy beyond paved roads. In this work, we consider the difficult problem of locomotion on challenging terrains using a single forward-facing depth camera. Due to the partial observability of the problem, the robot has to rely on past observations to infer the terrain currently beneath it. To solve this problem, we follow the paradigm in computer vision that explicitly models the 3D geometry of the scene and propose Neural Volumetric Memory (NVM), a geometric memory architecture that explicitly accounts for the SE(3) equivariance of the 3D world. NVM aggregates feature volumes from multiple camera views by first bringing them back to the ego-centric frame of the robot. We test the learned visual-locomotion policy on a physical robot and show that our approach, which explicitly introduces geometric priors during training, offers superior performance than more naïve methods. We also include ablation studies and show that the representations stored in the neural volumetric memory capture sufficient geometric information to reconstruct the scene. Our project page with videos is https://rchalyang.github.io/NVM Ruihan Yang, Xiaolong Wang 0004	CVPR	3
2023	ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs abstract While NeRF-based human representations have shown impressive novel view synthesis results, most methods still rely on a large number of images / views for training. In this work, we propose a novel animatable NeRF called ActorsNeRF. It is first pre-trained on diverse human subjects, and then adapted with few-shot monocular video frames for a new actor with unseen poses. Building on previous generalizable NeRFs with parameter sharing using a ConvNet encoder, ActorsNeRF further adopts two human priors to capture the large human appearance, shape, and pose variations. Specifically, in the encoded feature space, we will first align different human subjects in a category-level canonical space, and then align the same human from different frames in an instance-level canonical space for rendering. We quantitatively and qualitatively demonstrate that ActorsNeRF significantly outperforms the existing state-of-the-art on few-shot generalization to new people and poses on multiple datasets. Project page: https://jitengmu.github.io/ActorsNeRF/. Jiteng Mu, Shen Sang, Nuno Vasconcelos, Xiaolong Wang 0004	ICCV	4
2023	FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models abstract Recent works on generalizable NeRFs have shown promising results on novel view synthesis from single or few images. However, such models have rarely been applied on other downstream tasks beyond synthesis such as semantic understanding and parsing. In this paper, we propose a novel framework named FeatureNeRF to learn generalizable NeRFs by distilling pre-trained vision foundation models (e.g., DINO, Latent Diffusion). FeatureNeRF leverages 2D pre-trained foundation models to 3D space via neural rendering, and then extract deep features for 3D query points from NeRF MLPs. Consequently, it allows to map 2D images to continuous 3D semantic feature volumes, which can be used for various downstream tasks. We evaluate FeatureNeRF on tasks of 2D/3D semantic keypoint transfer and 2D/3D object part segmentation. Our extensive experiments demonstrate the effectiveness of FeatureNeRF as a generalizable 3D semantic feature extractor. Our project page is available at https://jianglongye.com/featurenerf/. Jianglong Ye, Naiyan Wang, Xiaolong Wang 0004	ICCV	3
2023	MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations Nicklas Hansen 0001, Hao Su 0001, Xiaolong Wang 0004, Aravind Rajeswaran	ICLR	4
2023	GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation Chenhongyi Yang, Shalini De Mello, Elliot Crowley, Xiaolong Wang 0004	ICLR	5
2023	Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild Shubhankar Borse, Fatih Porikli, Xiaolong Wang 0004	ICLR	6
2023	On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline abstract In this paper, we examine the effectiveness of pre-training for visuo-motor control tasks. We revisit a simple Learning-from-Scratch (LfS) baseline that incorporates data augmentation and a shallow ConvNet, and find that this baseline is surprisingly competitive with recent approaches (PVR, MVP, R3M) that leverage frozen visual representations trained on large-scale vision datasets – across a variety of algorithms, task domains, and metrics in simulation and on a real robot. Our results demonstrate that these methods are hindered by a significant domain gap between the pre-training datasets and current benchmarks for visuo-motor control, which is alleviated by finetuning. Based on our findings, we provide recommendations for future research in pre-training for control and hope that our simple yet strong baseline will aid in accurately benchmarking progress in this area. Code: https://github.com/gemcollector/learning-from-scratch. Nicklas Hansen 0001, Zhecheng Yuan, Yanjie Ze, Tongzhou Mu, Aravind Rajeswaran, Hao Su 0001, Huazhe Xu, Xiaolong Wang 0004	ICML	8
2023	MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses abstract We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follows an Autoencoder-based architecture, where the encoder estimates the monocular depth and the camera pose, and the decoder constructs a Multiplane NeRF representation based on the depth encoder feature, and renders the input frames with the estimated camera. The learning is supervised by the reconstruction error. Once the model is learned, it can be applied to multiple applications including depth estimation, camera pose estimation, and single-image novel view synthesis. More qualitative results are available at: https://oasisyang.github.io/mononerf. Ishan Misra, Xiaolong Wang 0004	ICML	3
2023	Learning Dense Correspondences between Photos and Sketches abstract Humans effortlessly grasp the connection between sketches and real-world objects, even when these sketches are far from realistic. Moreover, human sketch understanding goes beyond categorization -- critically, it also entails understanding how individual elements within a sketch correspond to parts of the physical world it represents. What are the computational ingredients needed to support this ability? Towards answering this question, we make two contributions: first, we introduce a new sketch-photo correspondence benchmark, PSC6k, containing 150K annotations of 6250 sketch-photo pairs across 125 object categories, augmenting the existing Sketchy dataset with fine-grained correspondence metadata. Second, we propose a self-supervised method for learning dense correspondences between sketch-photo pairs, building upon recent advances in correspondence learning for pairs of photos. Our model uses a spatial transformer network to estimate the warp flow between latent representations of a sketch and photo extracted by a contrastive learning-based ConvNet backbone. We found that this approach outperformed several strong baselines and produced predictions that were quantitatively consistent with other warp-based methods. However, our benchmark also revealed systematic differences between predictions of the suite of models we tested and those of humans. Taken together, our work suggests a promising path towards developing artificial systems that achieve more human-like understanding of visual images at different levels of abstraction. Project page: https://photo-sketch-correspondence.github.io Xuanchen Lu, Xiaolong Wang 0004, Judith E. Fan	ICML	2
2023	Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning abstract Bimanual manipulation is important for building intelligent robots that unlock richer skills than single arms. We consider a multi-object bimanual rearrangement task, where a reinforcement learning (RL) agent aims to jointly control two arms to rearrange these objects as fast as possible. Solving this task efficiently is challenging for an RL agent due to the requirement of discovering precise intra-arm coordination in an exponentially large control space. We develop a symmetry-aware actor-critic framework that leverages the interchangeable roles of the two manipulators in the bimanual control setting to reduce the policy search space. To handle the compositionality over multiple objects, we augment training data with an object-centric relabeling technique. The overall approach produces an RL policy that can rearrange up to 8 objects with a success rate of over 70% in simulation. We deploy the policy to two Franka Panda arms and further show a successful demo on human-robot collaboration. Videos can be found at https://sites.google.com/view/bimanual. Yunfei Li 0005, Chaoyi Pan, Huazhe Xu, Xiaolong Wang 0004, Yi Wu 0013	ICRA	4
2023	Elastic Decision Transformer abstract This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical evidence suggests it struggles with trajectory stitching, a process involving the generation of an optimal or near-optimal trajectory from the best parts of a set of sub-optimal trajectories. The proposed EDT differentiates itself by facilitating trajectory stitching during action inference at test time, achieved by adjusting the history length maintained in DT. Further, the EDT optimizes the trajectory by retaining a longer history when the previous trajectory is optimal and a shorter one when it is sub-optimal, enabling it to "stitch" with a more optimal trajectory. Extensive experimentation demonstrates EDT's ability to bridge the performance gap between DT-based and Q Learning-based approaches. In particular, the EDT outperforms Q Learning-based methods in a multi-task regime on the D4RL locomotion benchmark and Atari games. Yueh-Hua Wu, Xiaolong Wang 0004, Masashi Hamaya	NeurIPS	2
2022	VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution abstract Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent works of Space-Time Video Super-Resolution (STVSR) are developed to incorporate temporal interpolation and spatial super-resolution in a unified framework. However, most of them only support a fixed up-sampling scale, which limits their flexibility and applications. In this work, instead of following the discrete representations, we propose Video Implicit Neural Representation (VideoINR), and we show its applications for STVSR. The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales and significantly outperforms prior works on continuous and out-of-training-distribution scales. Our project page is at here and code is available at https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution. Yinbo Chen, Xingqian Xu, Vidit Goel, Zhangyang Wang, Humphrey Shi, Xiaolong Wang 0004	CVPR	8
2022	Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos abstract We propose to forecast future hand-object interactions given an egocentric video. Instead of predicting action labels or pixels, we directly predict the hand motion trajectory and the future contact points on the next active object (i.e., interaction hotspots). This relatively low-dimensional representation provides a con-crete description of future interactions. To tackle this task, we first provide an automatic way to collect trajectory and hotspots labels on large-scale data. We then use this data to train an Object-Centric Transformer (OCT) model for prediction. Our model performs hand and object interaction reasoning via the self-attention mechanism in Transformers. OCT also provides a probabilistic framework to sample the future trajectory and hotspots to handle uncertainty in prediction. We perform experi-ments on the Epic-Kitchens-55, Epic-Kitchens-100 and EGTEA Gaze+ datasets, and show that OCT significantly outperforms state-of the-art approaches by a large margin. Project page is available at https://stevenlsw.github.io/hoi-forecast. Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang 0004	CVPR	4
2022	CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs abstract Recent advances show that Generative Adversarial Networks (GANs) can synthesize images with smooth variations along semantically meaningful latent directions, such as pose, expression, layout, etc. While this indicates that GANs implicitly learn pixel-level correspondences across images, few studies explored how to extract them explicitly. In this work, we introduce Coordinate GAN (CoordGAN), a structure-texture disentangled GAN that learns a dense correspondence map for each generated image. We represent the correspondence maps of different images as warped coordinate frames transformed from a canonical coordinate frame, i.e., the correspondence map, which describes the structure (e.g., the shape of a face), is controlled via a transformation. Hence, finding correspondences boils down to locating the same coordinate in different correspondence maps. In CoordGAN, we sample a transformation to represent the structure of a synthesized instance, while an independent texture branch is responsible for rendering appearance details orthogonal to the structure. Our approach can also extract dense correspondence maps for real images by adding an encoder on top of the generator. We quantitatively demonstrate the quality of the learned dense correspondences through segmentation mask transfer on multiple datasets. We also show that the proposed generator achieves better structure and texture disentanglement compared to existing approaches. Project page: https://jitengmu.github.io/CoordGAN/ Jiteng Mu, Shalini De Mello, Zhiding Yu, Nuno Vasconcelos, Xiaolong Wang 0004, Jan Kautz, Sifei Liu	CVPR	5
2022	Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image abstract Novel view synthesis from a single image has recently attracted a lot of attention, and it has been primarily advanced by 3D deep learning and rendering techniques. However, most work is still limited by synthesizing new views within relatively small camera motions. In this paper, we propose a novel approach to synthesize a consistent long-term video given a single scene image and a trajectory of large camera motions. Our approach utilizes an autoregressive Transformer to perform sequential modeling of multiple frames, which reasons the relations between multiple frames and the corresponding cameras to predict the next frame. To facilitate learning and ensure consistency among generated frames, we introduce a locality constraint based on the input cameras to guide self-attention among a large number of patches across space and time. Our method outperforms state-of-the-art view synthesis approaches by a large margin, especially when synthesizing long-term future in indoor 3D scenes. Project page at https://xrenaa.github.io/look-outside-room/. Xuanchi Ren, Xiaolong Wang 0004	CVPR	2
2022	GroupViT: Semantic Segmentation Emerges from Text Supervision abstract Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens implicitly via top-down supervision from pixel-level recognition labels. Instead, in this paper, we propose to bring back the grouping mechanism into deep networks, which allows semantic segments to emerge automatically with only text supervision. We propose a hierarchical Grouping Vision Transformer (GroupViT), which goes beyond the regular grid structure representation and learns to group image regions into progressively larger arbitrary-shaped segments. We train GroupViT jointly with a text encoder on a large-scale image-text dataset via contrastive losses. With only text supervision and without any pixel-level annotations, GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner, i.e., without any further fine-tuning. It achieves a zero-shot accuracy of 52.3% mIoU on the PASCAL VOC 2012 and 22.4% mIoU on PASCAL Context datasets, and performs competitively to state-of-the-art transfer-learning methods requiring greater levels of supervision. We open-source our code at https://github.com/NVlabs/GroupViT. Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas M. Breuel, Jan Kautz, Xiaolong Wang 0004	CVPR	7
2022	GIFS: Neural Implicit Function for General Shape Representation abstract Recent development of neural implicit function has shown tremendous success on high-quality 3D shape re-construction. However, most works divide the space into inside and outside of the shape, which limits their repre-senting power to single-layer and watertight shapes. This limitation leads to tedious data processing (converting non-watertight raw data to watertight) as well as the incapability of representing general object shapes in the real world. In this work, we propose a novel method to represent general shapes including non-watertight shapes and shapes with multi-layer surfaces. We introduce General Implicit Function for 3D Shape (GIFS), which models the relationships between every two points instead of the relationships between points and surfaces. Instead of dividing 3D space into predefined inside-outside regions, GIFS encodes whether two points are separated by any surface. Experiments on ShapeNet show that GIFS outperforms previous state-of-the-art methods in terms of reconstruction quality, rendering efficiency, and visual fidelity. Project page is available at https://jianglongye.com/gifs. Jianglong Ye, Yuntao Chen, Naiyan Wang, Xiaolong Wang 0004	CVPR	4
2022	Transformers as Meta-learners for Implicit Neural Representations Yinbo Chen, Xiaolong Wang 0004	ECCV (17)	2
2022	Learning Implicit Feature Alignment Function for Semantic Segmentation Hanzhe Hu, Yinbo Chen, Shubhankar Borse, Fatih Porikli, Xiaolong Wang 0004	ECCV (29)	7
2022	Scraping Textures from Natural Images for Synthesis and Editing Xiaolong Wang 0004, Ming-Hsuan Yang 0001, Alexei A. Efros, Sifei Liu	ECCV (15)	2
2022	DexMV: Imitation Learning for Dexterous Manipulation from Human Videos Yuzhe Qin, Yueh-Hua Wu, Hanwen Jiang, Ruihan Yang, Xiaolong Wang 0004	ECCV (39)	7
2022	Learning Continuous Environment Fields via Implicit Functions Shalini De Mello, Xiaolong Wang 0004, Ming-Hsuan Yang 0001, Jan Kautz, Sifei Liu	ICLR	3
2022	Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers Ruihan Yang, Nicklas Hansen 0001, Huazhe Xu, Xiaolong Wang 0004	ICLR	5
2022	Temporal Difference Learning for Model Predictive Control abstract Data-driven model predictive control has two key advantages over model-free methods: a potential for improved sample efficiency through model learning, and better performance as computational budget for planning increases. However, it is both costly to plan over long horizons and challenging to obtain an accurate model of the environment. In this work, we combine the strengths of model-free and model-based methods. We use a learned task-oriented latent dynamics model for local trajectory optimization over a short horizon, and use a learned terminal value function to estimate long-term return, both of which are learned jointly by temporal difference learning. Our method, TD-MPC, achieves superior sample efficiency and asymptotic performance over prior work on both state and image-based continuous control tasks from DMControl and Meta-World. Code and videos are available at https://nicklashansen.github.io/td-mpc. Nicklas Hansen 0001, Hao Su 0001, Xiaolong Wang 0004	ICML	3
2022	Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization abstract Developing robust vision-guided controllers for quadrupedal robots in complex environments with various obstacles, dynamical surroundings and uneven terrains is very challenging. While Reinforcement Learning (RL) provides a promising paradigm for agile locomotion skills with vision inputs in simulation, it is still very challenging to deploy the vision-guided RL policy in the real world. Our key insight is that the asynchronous multi-modal observations, caused by different latencies in different components of the real robot, create a large sim2real gap for a RL policy. In this paper, we propose Multi-Modal Delay Randomization (MMDR) to address this issue when training in simulation. Specifically, we randomize the selections for both the proprioceptive states and the visual observations in time during training, aiming to simulate the asynchronous inputs when deploying to the real robot. With this technique, we are able to train a RL policy for end-to-end locomotion control in simulation, which can be directly deployed on the real A1 quadruped robot running in the wild. We evaluate our method in different outdoor environments with complex terrain and obstacles. We show that the robot can smoothly maneuver at a high speed while avoiding the obstacles, achieving significant improvement over the baselines. Our project page with videos is at https://mehooz.github.io/mmdr-wild/. Chieko Sarah Imai, Marcin Kierebinski, Ruihan Yang, Yuzhe Qin, Xiaolong Wang 0004	IROS	7
2022	Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset abstract 6D object pose estimation is one of the fundamental problems in computer vision and robotics research. While a lot of recent efforts have been made on generalizing pose estimation to novel object instances within the same category, namely category-level 6D pose estimation, it is still restricted in constrained environments given the limited number of annotated data. In this paper, we collect Wild6D, a new unlabeled RGBD object video dataset with diverse instances and backgrounds. We utilize this data to generalize category-level 6D object pose estimation in the wild with semi-supervised learning. We propose a new model, called Rendering for Pose estimation network RePoNet), that is jointly trained using the free ground-truths with the synthetic data, and a silhouette matching objective function on the real-world data. Without using any 3D annotations on real data, our method outperforms state-of-the-art methods on the previous dataset and our Wild6D test set (with manual annotations for evaluation) by a large margin. Project page with Wild6D data: \url{https://oasisyang.github.io/semi-pose/}. Yanjie Ze, Xiaolong Wang 0004	NeurIPS	2
2021	Learning Continuous Image Representation With Local Implicit Image Function abstract How to represent an image? While the visual world is presented in a continuous manner, machines store and see the images in a discrete way with 2D arrays of pixels. In this paper, we seek to learn a continuous representation for images. Inspired by the recent progress in 3D reconstruction with implicit neural representation, we propose Local Implicit Image Function (LIIF), which takes an image coordinate and the 2D deep features around the coordinate as inputs, predicts the RGB value at a given coordinate as an output. Since the coordinates are continuous, LIIF can be presented in arbitrary resolution. To generate the continuous representation for images, we train an encoder with LIIF representation via a self-supervised task with superresolution. The learned continuous representation can be presented in arbitrary resolution even extrapolate to ×30 higher resolution, where the training tasks are not provided. We further show that LIIF representation builds a bridge between discrete and continuous representation in 2D, it naturally supports the learning tasks with size-varied image ground-truths and significantly outperforms the method with resizing the ground-truths. Our project page with code is at https://yinboc.github.io/liif/. Yinbo Chen, Sifei Liu, Xiaolong Wang 0004	CVPR	3
2021	Semi-Supervised 3D Hand-Object Poses Estimation With Interactions in Time abstract Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the ground-truths from a single image perfectly. To tackle these challenges, we propose a unified framework for estimating the 3D hand and object poses with semi-supervised learning. We build a joint learning framework where we perform explicit contextual reasoning between hand and object representations. Going beyond limited 3D annotations in a single image, we leverage the spatial-temporal consistency in large-scale hand-object videos as a constraint for generating pseudo labels in semi-supervised learning. Our method not only improves hand pose estimation in challenging real-world dataset, but also substantially improve the object pose which has fewer ground-truths per instance. By training with large-scale diverse videos, our model also generalizes better across multiple out-of-domain datasets. Project page and code: https://stevenlsw.github.io/Semi-Hand-Object Hanwen Jiang, Sifei Liu, Xiaolong Wang 0004	CVPR	5
2021	Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes abstract Synthesizing 3D human motion plays an important role in many graphics applications as well as understanding human activity. While many efforts have been made on generating realistic and natural human motion, most approaches neglect the importance of modeling human-scene interactions and affordance. On the other hand, affordance reasoning (e.g., standing on the floor or sitting on the chair) has mainly been studied with static human pose and gestures, and it has rarely been addressed with human motion. In this paper, we propose to bridge human motion synthesis and scene affordance reasoning. We present a hierarchical generative framework to synthesize long-term 3D human motion conditioning on the 3D scene structure. Building on this framework, we further enforce multiple geometry constraints between the human mesh and scene point clouds via optimization to improve realistic synthesis. Our experiments show significant improvements over previous approaches on generating natural and physically plausible human motion in a scene.1 Jiashun Wang, Huazhe Xu, Jingwei Xu 0005, Sifei Liu, Xiaolong Wang 0004	CVPR	5
2021	Robust Object Detection via Instance-Level Temporal Cycle Confusion abstract Building reliable object detectors that are robust to domain shifts, such as various changes in context, viewpoint, and object appearances, is critical for real-world applications. In this work, we study the effectiveness of auxiliary self-supervised tasks to improve the out-of-distribution generalization of object detectors. Inspired by the principle of maximum entropy, we introduce a novel self-supervised task, instance-level temporal cycle confusion (CycConf), which operates on the region features of the object detectors. For each object, the task is to find the most different object proposals in the adjacent frame in a video and then cycle back to itself for self-supervision. CycConf encourages the object detector to explore invariant structures across instances under various motions, which leads to improved model robustness in unseen domains at test time. We observe consistent out-of-domain performance improvements when training object detectors in tandem with self-supervised tasks on various do-main adaptation benchmarks with static images (Cityscapes, Foggy Cityscapes, Sim10K) and large-scale video datasets (BDD100K and Waymo open data)1. Xin Wang 0066, Thomas E. Huang, Benlin Liu, Fisher Yu 0001, Xiaolong Wang 0004, Joseph Gonzalez 0001, Trevor Darrell	ICCV	5
2021	Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning abstract Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear. In this paper, we explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard bench-marks. Our further analysis shed some light on understanding the trade-offs between the meta-learning objective and the whole-classification objective in few-shot learning. Our code is available at https://github.com/yinboc/few-shot-meta-baseline. Yinbo Chen, Zhuang Liu 0003, Huijuan Xu 0001, Trevor Darrell, Xiaolong Wang 0004	ICCV	5
2021	Hand-Object Contact Consistency Reasoning for Human Grasps Generation abstract While predicting robot grasps with parallel jaw grippers have been well studied and widely applied in robot manipulation tasks, the study on natural human grasp generation with a multi-finger hand remains a very challenging problem. In this paper, we propose to generate human grasps given a 3D object in the world. Our key observation is that it is crucial to model the consistency between the hand contact points and object contact regions. That is, we encourage the prior hand contact points to be close to the object surface and the object common contact regions to be touched by the hand at the same time. Based on the hand-object contact consistency, we design novel objectives in training the human grasp generation model and also a new self-supervised task which allows the grasp generation network to be adjusted even during test time. Our experiments show significant improvement in human grasp generation over state-of-the-art approaches by a large margin. More interestingly, by optimizing the model during test time with the self-supervised task, it helps achieve larger gain on unseen and out-of-domain objects. Project page: https://hwjiang1510.github.io/GraspTTA/. Hanwen Jiang, Jiashun Wang, Xiaolong Wang 0004	ICCV	4
2021	Video Autoencoder: self-supervised disentanglement of static 3D structure and motion abstract A video autoencoder is proposed for learning disentangled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in nearby video frames remains static. Given a sequence of video frames as input, the video autoencoder extracts a disentangled representation of the scene including: (i) a temporally-consistent deep voxel feature to represent the 3D structure and (ii) a 3D trajectory of camera pose for each frame. These two representations will then be re-entangled for rendering the input video frames. This video autoencoder can be trained directly using a pixel re-construction loss, without any ground truth 3D or camera pose annotations. The disentangled representation can be applied to a range of tasks, including novel view synthesis, camera pose estimation, and video generation by motion following. We evaluate our method on several large-scale natural video datasets, and show generalization results on out-of-domain images. Project page with code: https://zlai0.github.io/VideoAutoencoder. Zihang Lai, Sifei Liu, Alexei A. Efros, Xiaolong Wang 0004	ICCV	4
2021	Rethinking preventing class-collapsing in metric learning with margin-based losses abstract Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. Although theoretically with optimal assumptions, margin-based losses such as the triplet loss and margin loss have a diverse family of solutions. We theoretically prove and empirically show that under reasonable noise assumptions, margin-based losses tend to project all samples of a class with various modes onto a single point in the embedding space, resulting in class collapse that usually renders the space ill-sorted for classification or retrieval. To address this problem, we propose a simple modification to the embedding losses such that each sample selects its nearest same-class counterpart in a batch as the positive element in the tuple. This allows for the presence of multiple sub-clusters within each class. The adaptation can be integrated into a wide range of metric learning losses. Our method demonstrates clear benefits on various fine-grained image retrieval datasets over a variety of existing losses; qualitative retrieval results show that samples with similar visual patterns are indeed closer in the embedding space. Elad Levi, Tete Xiao, Xiaolong Wang 0004, Trevor Darrell	ICCV	3
2021	A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation abstract Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been devoted to modeling general articulated objects. Compared to rigid objects, articulated objects have higher degrees of freedom, which makes it hard to generalize to unseen shapes. To deal with the large shape variance, we introduce Articulated Signed Distance Functions (A-SDF) to represent articulated shapes with a disentangled latent space, where we have separate codes for encoding shape and articulation. With this disentangled continuous representation, we demonstrate that we can control the articulation input and animate unseen instances with unseen joint angles. Furthermore, we propose a Test-Time Adaptation inference algorithm to adjust our model during inference. We demonstrate our model generalize well to out-of-distribution and unseen data, e.g., partial point clouds and real-world depth images. Project page with code: https://jitengmu.github.io/A-SDF/. Jiteng Mu, Weichao Qiu, Adam Kortylewski, Alan L. Yuille, Nuno Vasconcelos, Xiaolong Wang 0004	ICCV	6
2021	Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency abstract Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instance are considered as a positive sample pair, where various tasks are designed to learn invariant representations by comparing the pair. Analogically, for video data, representations of frames from the same video are trained to be closer than frames from other videos, i.e. intra-video invariance. However, cross-video relation has barely been explored for visual representation learning. Unlike intra-video invariance, ground-truth labels of cross-video relation is usually unavailable without human labors. In this paper, we propose a novel contrastive learning method which explores the cross-video relation by using cycle-consistency for general image representation learning. This allows to collect positive sample pairs across different video instances, which we hypothesize will lead to higher-level semantics. We validate our method by transferring our image representation to multiple downstream tasks including visual object tracking, image classification, and action recognition. We show significant improvement over state-of-the-art contrastive learning methods. Project page is available at https://happywu.github.io/cycle_contrast_video. Haiping Wu, Xiaolong Wang 0004	ICCV	2
2021	Region Similarity Representation Learning abstract We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on solely learning global representations for an entire image, ReSim learns both regional representations for localization as well as semantic image-level representations. ReSim operates by sliding a fixed-sized window across the overlapping area between two views (e.g., image crops), aligning these areas with their corresponding convolutional feature map regions, and then maximizing the feature similarity across views. As a result, ReSim learns spatially and semantically consistent feature representation throughout the convolutional feature maps of a neural network. A shift or scale of an image region, e.g., a shift or scale of an object, has a corresponding change in the feature maps; this allows downstream tasks to leverage these representations for localization. Through object detection, instance segmentation, and dense pose estimation experiments, we illustrate how ReSim learns representations which significantly improve the localization and classification performance compared to a competitive MoCo-v2 baseline: $ + 2.7AP_{75}^{bb}VOC$, $ + 1.1AP_{75}^{bb}COCO$, and +1.9 APmkCityscapes. Code and pre-trained models are released at: https://github.com/Tete-Xiao/ReSim Tete Xiao, Colorado Reed, Xiaolong Wang 0004, Kurt Keutzer, Trevor Darrell	ICCV	3
2021	Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective abstract Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixel segmentation. To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning. Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. Our work is inspired by the recent success in image-level contrastive learning and similarity learning for visual recognition. Our hypothesis is that if the representation is good for recognition, it requires the convolutional features to find correspondence between similar objects or parts. Our experiments show surprising results that VFS surpasses state-of-the-art self-supervised approaches for both OTB visual object tracking and DAVIS video object segmentation. We perform detailed analysis on what matters in VFS and reveals new properties on image and frame level similarity learning. Project page with code: https://jerryxu.net/VFS. Xiaolong Wang 0004	ICCV	2
2021	Self-Supervised Policy Adaptation during Deployment Nicklas Hansen 0001, Rishabh Jangir, Yu Sun 0020, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang 0004	ICLR	8
2021	Solving Compositional Reinforcement Learning Problems via Task Reduction Yunfei Li 0005, Yilin Wu 0003, Huazhe Xu, Xiaolong Wang 0004, Yi Wu 0013	ICLR	4
2021	Learning Long-term Visual Dynamics with Region Proposal Interaction Networks Haozhi Qi, Xiaolong Wang 0004, Deepak Pathak, Yi Ma 0001, Jitendra Malik	ICLR	2
2021	Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization Zhenggang Tang, Chao Yu 0005, Boyuan Chen 0003, Huazhe Xu, Xiaolong Wang 0004, Fei Fang 0001, Simon S. Du, Yu Wang 0002, Yi Wu 0013	ICLR	5
2021	What Should Not Be Contrastive in Contrastive Learning Tete Xiao, Xiaolong Wang 0004, Alexei A. Efros, Trevor Darrell	ICLR	2
2021	Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency Tete Xiao, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang 0004	ICLR	5
2021	Compositional Video Synthesis with Action Graphs abstract Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed actions. To address this challenge, we propose to represent the actions in a graph structure called Action Graph and present the new "Action Graph To Video" synthesis task. Our generative model for this task (AG2Vid) disentangles motion and appearance features, and by incorporating a scheduling mechanism for actions facilitates a timely and coordinated video generation. We train and evaluate AG2Vid on CATER and Something-Something V2 datasets, which results in videos that have better visual quality and semantic consistency compared to baselines. Finally, our model demonstrates zero-shot abilities by synthesizing novel compositions of the learned actions. Amir Bar, Roei Herzig, Xiaolong Wang 0004, Anna Rohrbach, Gal Chechik, Trevor Darrell, Amir Globerson	ICML	3
2021	Generalization in Reinforcement Learning by Soft Data Augmentation abstract Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during training, optimization becomes increasingly challenging, and empirically may result in lower sample efficiency and unstable training. Instead of learning policies directly from augmented data, we propose SOft Data Augmentation (SODA), a method that decouples augmentation from policy learning. Specifically, SODA imposes a soft constraint on the encoder that aims to maximize the mutual information between latent representations of augmented and non-augmented data, while the RL optimization process uses strictly non-augmented data. Empirical evaluations are performed on diverse tasks from DeepMind Control suite as well as a robotic manipulation task, and we find SODA to significantly advance sample efficiency, generalization, and stability in training over state-of-the-art vision-based RL methods.1 Nicklas Hansen 0001, Xiaolong Wang 0004	ICRA	2
2021	State-Only Imitation Learning for Dexterous Manipulation abstract Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address this, current approaches employ expert demonstrations in the form of state-action pairs, which are difficult to obtain for real-world settings such as learning from videos. In this paper, we move toward a more realistic setting and explore state-only imitation learning. To tackle this setting, we train an inverse dynamics model and use it to predict actions for state-only demonstrations. The inverse dynamics model and the policy are trained jointly. Our method performs on par with state-action approaches and considerably outperforms RL alone. By not relying on expert actions, we are able to learn from demonstrations with different dynamics, morphologies, and objects. Videos available on the ${\text{project page}}$. Ilija Radosavovic, Xiaolong Wang 0004, Lerrel Pinto, Jitendra Malik	IROS	2
2021	Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation abstract While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments remains very challenging. Extensive use of data augmentation is a promising technique for improving generalization in RL, but it is often found to decrease sample efficiency and can even lead to divergence. In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms. We identify two problems, both rooted in high-variance Q-targets. Based on our findings, we propose a simple yet effective technique for stabilizing this class of algorithms under augmentation. We perform extensive empirical evaluation of image-based RL using both ConvNets and Vision Transformers (ViT) on a family of benchmarks based on DeepMind Control Suite, as well as in robotic manipulation tasks. Our method greatly improves stability and sample efficiency of ConvNets under augmentation, and achieves generalization results competitive with state-of-the-art methods for image-based RL in environments with unseen visuals. We further show that our method scales to RL with ViT-based architectures, and that data augmentation may be especially important in this setting. Nicklas Hansen 0001, Hao Su 0001, Xiaolong Wang 0004	NeurIPS	3
2021	Test-Time Personalization with a Transformer for Human Pose Estimation abstract We propose to personalize a 2D human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challenging for a model to generalize to different unknown environments and unseen persons. Instead of using a fixed model for every test case, we adapt our pose estimator during test time to exploit person-specific information. We first train our model on diverse data with both a supervised and a self-supervised pose estimation objectives jointly. We use a Transformer model to build a transformation between the self-supervised keypoints and the supervised keypoints. During test time, we personalize and adapt our model by fine-tuning with the self-supervised objective. The pose is then improved by transforming the updated self-supervised keypoints. We experiment with multiple datasets and show significant improvements on pose estimations with our self-supervised personalization. Project page with code is available at https://liyz15.github.io/TTP/. Yizhuo Li 0001, Miao Hao, Zonglin Di, Nitesh B. Gundavarapu, Xiaolong Wang 0004	NeurIPS	5
2021	Multi-Person 3D Motion Prediction with Multi-Range Transformers abstract We propose a novel framework for multi-person 3D motion trajectory prediction. Our key observation is that a human's action and behaviors may highly depend on the other persons around. Thus, instead of predicting each human pose trajectory in isolation, we introduce a Multi-Range Transformers model which contains of a local-range encoder for individual motion and a global-range encoder for social interactions. The Transformer decoder then performs prediction for each person by taking a corresponding pose as a query which attends to both local and global-range encoder features. Our model not only outperforms state-of-the-art methods on long-term 3D motion prediction, but also generates diverse social interactions. More interestingly, our model can even predict 15-person motion simultaneously by automatically dividing the persons into different interaction groups. Project page with code is available at https://jiashunwang.github.io/MRT/. Jiashun Wang, Huazhe Xu, Medhini Narasimhan, Xiaolong Wang 0004	NeurIPS	4
2021	NovelD: A Simple yet Effective Exploration Criterion abstract Efficient exploration under sparse rewards remains a key challenge in deep reinforcement learning. Previous exploration methods (e.g., RND) have achieved strong results in multiple hard tasks. However, if there are multiple novel areas to explore, these methods often focus quickly on one without sufficiently trying others (like a depth-wise first search manner). In some scenarios (e.g., four corridor environment in Sec 4.2), we observe they explore in one corridor for long and fail to cover all the states. On the other hand, in theoretical RL, with optimistic initialization and the inverse square root of visitation count as a bonus, it won't suffer from this and explores different novel regions alternatively (like a breadth-first search manner). In this paper, inspired by this, we propose a simple but effective criterion called NovelD by weighting every novel area approximately equally. Our algorithm is very simple but yet shows comparable performance or even outperforms multiple SOTA exploration methods in many hard exploration tasks. Specifically, NovelD solves all the static procedurally-generated tasks in Mini-Grid with just 120M environment steps, without any curriculum learning. In comparison, the previous SOTA only solves 50% of them. NovelD also achieves SOTA on multiple tasks in NetHack, a rogue-like game that contains more challenging procedurally-generated environments. In multiple Atari games (e.g., MonteZuma's Revenge, Venture, Gravitar), NovelD outperforms RND. We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary. Tianjun Zhang, Huazhe Xu, Xiaolong Wang 0004, Yi Wu 0013, Kurt Keutzer, Joseph Gonzalez 0001, Yuandong Tian	NeurIPS	3
2020	Something-Else: Compositional Action Recognition With Spatial-Temporal Interaction Networks abstract Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category. Joanna Materzynska, Tete Xiao, Roei Herzig, Huijuan Xu 0001, Xiaolong Wang 0004, Trevor Darrell	CVPR	5
2020	Hierarchical Style-Based Networks for Motion Synthesis Jingwei Xu 0005, Huazhe Xu, Bingbing Ni, Xiaokang Yang 0001, Xiaolong Wang 0004, Trevor Darrell	ECCV (11)	5
2020	Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning Qian Long, Zihan Zhou 0002, Abhinav Gupta 0001, Fei Fang 0001, Yi Wu 0013, Xiaolong Wang 0004	ICLR	6
2020	Deep Isometric Learning for Visual Recognition abstract Initialization, normalization, and skip connections are believed to be three indispensable techniques for training very deep convolutional neural networks and obtaining state-of-the-art performance. This paper shows that deep vanilla ConvNets without normalization nor skip connections can also be trained to achieve surprisingly good performance on standard image recognition benchmarks. This is achieved by enforcing the convolution kernels to be near isometric during initialization and training, as well as by using a variant of ReLU that is shifted towards being isometric. Further experiments show that if combined with skip connections, such near isometric networks can achieve performances on par with (for ImageNet) and better than (for COCO) the standard ResNet, even without normalization at all. Our code is available at https://github.com/HaozhiQi/ISONet. Haozhi Qi, Chong You, Xiaolong Wang 0004, Yi Ma 0001, Jitendra Malik	ICML	3
2020	Test-Time Training with Self-Supervision for Generalization under Distribution Shifts abstract In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts. Yu Sun 0020, Xiaolong Wang 0004, Zhuang Liu 0003, John Miller 0001, Alexei A. Efros, Moritz Hardt	ICML	2
2020	Online Adaptation for Consistent Mesh Reconstruction in the Wild abstract This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D keypoints, or camera pose for each video frame, we pose video-based reconstruction as a self-supervised online adaptation problem applied to any incoming test video. We first learn a category-specific 3D reconstruction model from a collection of single-view images of the same category that jointly predicts the shape, texture, and camera pose of an image. Then, at inference time, we adapt the model to a test video over time using self-supervised regularization terms that exploit temporal consistency of an object instance to enforce that all reconstructed meshes share a common texture map, a base shape, as well as parts. We demonstrate that our algorithm recovers temporally consistent and reliable 3D structures from videos of non-rigid objects including those of animals captured in the wild -- an extremely challenging task rarely addressed before. Sifei Liu, Shalini De Mello, Xiaolong Wang 0004, Ming-Hsuan Yang 0001, Jan Kautz	NeurIPS	5
2020	Multi-Task Reinforcement Learning with Soft Modularization abstract Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other. Thus, instead of naively sharing parameters across tasks, we introduce an explicit modularization technique on policy representation to alleviate this optimization issue. Given a base policy network, we design a routing network which estimates different routing strategies to reconfigure the base network for each task. Instead of directly selecting routes for each task, our task-specific policy uses a method called soft modularization to softly combine all the possible routes, which makes it suitable for sequential tasks. We experiment with various robotics manipulation tasks in simulation and show our method improves both sample efficiency and performance over strong baselines by a large margin. Ruihan Yang, Huazhe Xu, Yi Wu 0013, Xiaolong Wang 0004	NeurIPS	4
2019	Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments abstract Affordance modeling plays an important role in visual understanding. In this paper, we aim to predict affordances of 3D indoor scenes, specifically what human poses are afforded by a given indoor environment, such as sitting on a chair or standing on the floor. In order to predict valid affordances and learn possible 3D human poses in indoor scenes, we need to understand the semantic and geometric structure of a scene as well as its potential interactions with a human. To learn such a model, a large-scale dataset of 3D indoor affordances is required. In this work, we build a fully automatic 3D pose synthesizer that fuses semantic knowledge from a large number of 2D poses extracted from TV shows as well as 3D geometric knowledge from voxel representations of indoor scenes. With the data created by the synthesizer, we introduce a 3D pose generative model to predict semantically plausible and physically feasible human poses within a given scene (provided as a single RGB, RGB-D, or depth image). We demonstrate that our human affordance prediction method consistently outperforms existing state-of-the-art methods. Sifei Liu, Xiaolong Wang 0004, Ming-Hsuan Yang 0001, Jan Kautz	CVPR	4
2019	Learning Correspondence From the Cycle-Consistency of Time abstract We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time, our model learns a feature map representation to be useful for performing cycle-consistent tracking. At test time, we use the acquired representation to find nearest neighbors across space and time. We demonstrate the generalizability of the representation -- without finetuning -- across a range of visual correspondence tasks, including video object segmentation, keypoint tracking, and optical flow. Our approach outperforms previous self-supervised methods and performs competitively with strongly supervised methods. Xiaolong Wang 0004, Allan Jabri, Alexei A. Efros	CVPR	1
2019	Visual Semantic Navigation using Scene Priors Wei Yang 0019, Xiaolong Wang 0004, Ali Farhadi, Abhinav Gupta 0001, Roozbeh Mottaghi	ICLR (Poster)	2
2019	Joint-task Self-supervised Learning for Temporal Correspondence abstract This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions and establishing fine-grained pixel-level associations between consecutive video frames. We exploit the synergy between both tasks through a shared inter-frame affinity matrix, which simultaneously models transitions between video frames at both the region- and pixel-levels. While region-level localization helps reduce ambiguities in fine-grained matching by narrowing down search regions; fine-grained matching provides bottom-up features to facilitate region-level localization. Our method outperforms the state-of-the-art self-supervised methods on a variety of visual correspondence tasks, including video-object and part-segmentation propagation, keypoint tracking, and object tracking. Our self-supervised method even surpasses the fully-supervised affinity feature representation obtained from a ResNet-18 pre-trained on the ImageNet. Sifei Liu, Shalini De Mello, Xiaolong Wang 0004, Jan Kautz, Ming-Hsuan Yang 0001	NeurIPS	4
2018	Non-Local Neural Networks abstract Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our non-local models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code is available at https://github.com/facebookresearch/video-nonlocal-net . Xiaolong Wang 0004, Ross B. Girshick, Abhinav Gupta 0001, Kaiming He	CVPR	1
2018	Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs abstract We consider the problem of zero-shot recognition: learning a visual classifier for a category with zero training examples, just using the word embedding of the category and its relationship to other categories, which visual data are provided. The key to dealing with the unfamiliar or novel category is to transfer knowledge obtained from familiar classes to describe the unfamiliar class. In this paper, we build upon the recently introduced Graph Convolutional Network (GCN) and propose an approach that uses both semantic embeddings and the categorical relationships to predict the classifiers. Given a learned knowledge graph (KG), our approach takes as input semantic embeddings for each node (representing visual category). After a series of graph convolutions, we predict the visual classifier for each category. During training, the visual classifiers for a few categories are given to learn the GCN parameters. At test time, these filters are used to predict the visual classifiers of unseen categories. We show that our approach is robust to noise in the KG. More importantly, our approach provides significant improvement in performance compared to the current state-of-the-art results (from 2 ~ 3% on some metrics to whopping 20% on a few). Xiaolong Wang 0004, Yufei Ye 0001, Abhinav Gupta 0001	CVPR	1
2018	3D Human Pose Estimation in the Wild by Adversarial Learning abstract Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations. Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild. We also observe that a carefully designed information source for the discriminator is essential to boost the performance. Thus, we design a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator. The efficacy of our adversarial learning framework with the new geometric descriptor has been demonstrated through extensive experiments on widely used public benchmarks. Our approach significantly improves the performance compared with previous state-of-the-art approaches. Wei Yang 0019, Wanli Ouyang, Xiaolong Wang 0004, Jimmy S. J. Ren, Hongsheng Li 0001, Xiaogang Wang 0001	CVPR	3
2018	Videos as Space-Time Region Graphs Xiaolong Wang 0004, Abhinav Gupta 0001	ECCV (5)	1
2018	Interpretable Intuitive Physics Model Tian Ye 0006, Xiaolong Wang 0004, James Davidson, Abhinav Gupta 0001	ECCV (12)	2
2017	Binge Watching: Scaling Affordance Learning from Sitcoms abstract In recent years, there has been a renewed interest in jointly modeling perception and action. At the core of this investigation is the idea of modeling affordances. However, when it comes to predicting affordances, even the state of the art approaches still do not use any ConvNets. Why is that? Unlike semantic or 3D tasks, there still does not exist any large-scale dataset for affordances. In this paper, we tackle the challenge of creating one of the biggest dataset for learning affordances. We use seven sitcoms to extract a diverse set of scenes and how actors interact with different objects in the scenes. Our dataset consists of more than 10K scenes and 28K ways humans can interact with these 10K images. We also propose a two-step approach to predict affordances in a new scene. In the first step, given a location in the scene we classify which of the 30 pose classes is the likely affordance pose. Given the pose class and the scene, we then use a Variational Autoencoder (VAE) [23] to extract the scale and deformation of the pose. The VAE allows us to sample the distribution of possible poses at test time. Finally, we show the importance of large-scale data in learning a generalizable and robust model of affordances. Xiaolong Wang 0004, Rohit Girdhar, Abhinav Gupta 0001	CVPR	1
2017	A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection abstract How do we learn an object detector that is invariant to occlusions and deformations? Our current solution is to use a data-driven strategy - collect large-scale datasets which have object instances under different conditions. The hope is that the final classifier can use these examples to learn invariances. But is it really possible to see all the occlusions in a dataset? We argue that like categories, occlusions and object deformations also follow a long-tail. Some occlusions and deformations are so rare that they hardly happen, yet we want to learn a model invariant to such occurrences. In this paper, we propose an alternative solution. We propose to learn an adversarial network that generates examples with occlusions and deformations. The goal of the adversary is to generate examples that are difficult for the object detector to classify. In our framework both the original detector and adversary are learned in a joint manner. Our experimental results indicate a 2.3% mAP boost on VOC07 and a 2.6% mAP boost on VOC2012 object detection challenge compared to the Fast-RCNN pipeline. Xiaolong Wang 0004, Abhinav Shrivastava, Abhinav Gupta 0001	CVPR	1
2017	Transitive Invariance for Self-Supervised Visual Representation Learning abstract Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of invariance useful for recognition. In this paper, we propose to exploit different self-supervised approaches to learn representations invariant to (i) inter-instance variations (two objects in the same class should have similar features) and (ii) intra-instance variations (viewpoint, pose, deformations, illumination, etc.). Instead of combining two approaches with multi-task learning, we argue to organize and reason the data with multiple variations. Specifically, we propose to generate a graph with millions of objects mined from hundreds of thousands of videos. The objects are connected by two types of edges which correspond to two types of invariance: “different instances but a similar viewpoint and category” and “different viewpoints of the same instance”. By applying simple transitivity on the graph with these edges, we can obtain pairs of images exhibiting richer visual invariance. We use this data to train a Triplet-Siamese network with VGG16 as the base architecture and apply the learned representations to different recognition tasks. For object detection, we achieve 63.2% mAP on PASCAL VOC 2007 using Fast R-CNN (compare to 67.3% with ImageNet pre-training). For the challenging COCO dataset, our method is surprisingly close (23.5%) to the ImageNet-supervised counterpart (24.4%) using the Faster R-CNN framework. We also show that our network can perform significantly better than the ImageNet network in the surface normal estimation task. Xiaolong Wang 0004, Kaiming He, Abhinav Gupta 0001	ICCV	1
2017	Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection abstract In this paper, we investigate a weakly-supervised object detection framework. Most existing frameworks focus on using static images to learn object detectors. However, these detectors often fail to generalize to videos because of the existing domain shift. Therefore, we investigate learning these detectors directly from boring videos of daily activities. Instead of using bounding boxes, we explore the use of action descriptions as supervision since they are relatively easy to gather. A common issue, however, is that objects of interest that are not involved in human actions are often absent in global action descriptions known as “missing label”. To tackle this problem, we propose a novel temporal dynamic graph Long Short-Term Memory network (TDGraph LSTM). TD-Graph LSTM enables global temporal reasoning by constructing a dynamic graph that is based on temporal correlations of object proposals and spans the entire video. The missing label issue for each individual frame can thus be significantly alleviated by transferring knowledge across correlated objects proposals in the whole video. Extensive evaluations on a large-scale daily-life action dataset (i.e., Charades) demonstrates the superiority of our proposed method. We also release object bounding-box annotations for more than 5,000 frames in Charades. We believe this annotated data can also benefit other research on video-based object recognition in the future. Yuan Yuan 0002, Xiaodan Liang, Xiaolong Wang 0004, Dit-Yan Yeung, Abhinav Gupta 0001	ICCV	3
2016	Actions ~ Transformations abstract What defines an action like "kicking ball"? We argue that the true meaning of an action lies in the change or transformation an action brings to the environment. In this paper, we propose a novel representation for actions by modeling an action as a transformation which changes the state of the environment before the action happens (precondition) to the state after the action (effect). Motivated by recent advancements of video representation using deep learning, we design a Siamese network which models the action as a transformation on a high-level feature space. We show that our model gives improvements on standard action recognition datasets including UCF101 and HMDB51. More importantly, our approach is able to generalize beyond learned action categories and shows significant performance improvement on cross-category generalization on our new ACT dataset. Xiaolong Wang 0004, Ali Farhadi, Abhinav Gupta 0001	CVPR	1
2016	Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding Gunnar A. Sigurdsson, Gül Varol, Xiaolong Wang 0004, Ali Farhadi, Ivan Laptev, Abhinav Gupta 0001	ECCV (1)	3
2016	Generative Image Modeling Using Style and Structure Adversarial Networks Xiaolong Wang 0004, Abhinav Gupta 0001	ECCV (4)	1
2015	Designing deep networks for surface normal estimation abstract In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture? We propose to build upon the decades of hard work in 3D scene understanding to design a new CNN architecture for the task of surface normal estimation. We show that incorporating several constraints (man-made, Manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning. Xiaolong Wang 0004, David F. Fouhey, Abhinav Gupta 0001	CVPR	1
2015	Unsupervised Learning of Visual Representations Using Videos abstract Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful approach for unsupervised learning of CNN. Specifically, we use hundreds of thousands of unlabeled videos from the web to learn visual representations. Our key idea is that visual tracking provides the supervision. That is, two patches connected by a track should have similar visual representation in deep feature space since they probably belong to same object or object part. We design a Siamese-triplet network with a ranking loss function to train this CNN representation. Without using a single image from ImageNet, just using 100K unlabeled videos and the VOC 2012 dataset, we train an ensemble of unsupervised networks that achieves 52% mAP (no bounding box regression). This performance comes tantalizingly close to its ImageNet-supervised counterpart, an ensemble which achieves a mAP of 54.4%. We also show that our unsupervised network can perform competitively in other tasks such as surface-normal estimation. Xiaolong Wang 0004, Abhinav Gupta 0001	ICCV	1
2015	Discriminatively Trained And-Or Graph Models for Object Shape Detection abstract In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images. Our proposed model consists of four layers: leaf-nodes at the bottom are local classifiers for detecting contour fragments; or-nodes above the leaf-nodes function as the switches to activate their child leaf-nodes, making the model reconfigurable during inference; and-nodes in a higher layer capture holistic shape deformations; one root-node on the top, which is also an or-node, activates one of its child and-nodes to deal with large global variations (e.g. different poses and views). We propose a novel structural optimization algorithm to discriminatively train the And-Or model from weakly annotated data. This algorithm iteratively determines the model structures (e.g. the nodes and their layouts) along with the parameter learning. On several challenging datasets, our model demonstrates the effectiveness to perform robust shape-based object detection against background clutter and outperforms the other state-of-the-art approaches. We also release a new shape database with annotations, which includes more than 1500 challenging shape instances, for recognition and detection. Liang Lin 0004, Xiaolong Wang 0004, Wei Yang 0019, Jian-Huang Lai	IEEE Trans. Pattern Anal. Mach. Intell.	2
2014	An expressive deep model for human action parsing from a single image abstract This paper aims at one newly raising task in vision and multimedia research: recognizing human actions from still images. Its main challenges lie in the large variations in human poses and appearances, as well as the lack of temporal motion information. Addressing these problems, we propose to develop an expressive deep model to naturally integrate human layout and surrounding contexts for higher level action understanding from still images. In particular, a Deep Belief Net is trained to fuse information from different noisy sources such as body part detection and object detection. To bridge the semantic gap, we used manually labeled data to greatly improve the effectiveness and efficiency of the pre-training and fine-tuning stages of the DBN training. The resulting framework is shown to be robust to sometimes unreliable inputs (e.g., imprecise detections of human parts and objects), and outperforms the state-of-the-art approaches. Zhujin Liang, Xiaolong Wang 0004, Rui Huang 0001, Liang Lin 0004	ICME	2
2014	3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks abstract Human activity understanding with 3D/depth sensors has received increasing attention in multimedia processing and interactions. This work targets on developing a novel deep model for automatic activity recognition from RGB-D videos. We represent each human activity as an ensemble of cubic-like video segments, and learn to discover the temporal structures for a category of activities, i.e. how the activities to be decomposed in terms of classification. Our model can be regarded as a structured deep architecture, as it extends the convolutional neural networks (CNNs) by incorporating structure alternatives. Specifically, we build the network consisting of 3D convolutions and max-pooling operators over the video segments, and introduce the latent variables in each convolutional layer manipulating the activation of neurons. Our model thus advances existing approaches in two aspects: (i) it acts directly on the raw inputs (grayscale-depth data) to conduct recognition instead of relying on hand-crafted features, and (ii) the model structure can be dynamically adjusted accounting for the temporal variations of human activities, i.e. the network configuration is allowed to be partially activated during inference. For model training, we propose an EM-type optimization method that iteratively (i) discovers the latent structure by determining the decomposed actions for each training example, and (ii) learns the network parameters by using the back-propagation algorithm. Our approach is validated in challenging scenarios, and outperforms state-of-the-art methods. A large human activity database of RGB-D videos is presented in addition. Keze Wang, Xiaolong Wang 0004, Liang Lin 0004, Meng Wang 0001, Wangmeng Zuo	ACM Multimedia	2
2014	Deep Joint Task Learning for Generic Object Extraction Xiaolong Wang 0004, Liliang Zhang, Liang Lin 0004, Zhujin Liang, Wangmeng Zuo	NIPS	1
2013	Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection abstract This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance. Compared with well acknowledged hierarchical models, we study two advanced capabilities in hierarchy for object modeling: (i)``switch'' variables(i.e. or-nodes) for specifying alternative compositions, and (ii) making local classifiers (i.e. leaf-nodes) shared among different classes. These capabilities enable us to account well for structural variabilities while preserving the model compact. Our model, in the form of an And-Or Graph, comprises four layers: a batch of leaf-nodes with collaborative edges in bottom for localizing object parts, the or-nodes over bottom to activate their children leaf-nodes, the and-nodes to classify objects as a whole, one root-node on the top for switching multiclass classification, which is also an or-node. For model training, we present an EM-type algorithm, namely dynamical structural optimization (DSO), to iteratively determine the structural configuration, (e.g., leaf-node generation associated with their parent or-nodes and shared across other classes), along with optimizing multi-layer parameters. The proposed method is valid on challenging databases, e.g., PASCAL VOC 2007 and UIUC-People, and it achieves state-of-the-arts performance. Xiaolong Wang 0004, Liang Lin 0004, Lichao Huang, Shuicheng Yan	CVPR	1
2012	Learning contour-fragment-based shape model with And-Or tree representation abstract This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree. This model extends the traditional hierarchical tree structures by introducing the “switch” variables (i.e. the or-nodes) that explicitly specify production rules to capture shape variations. We thus define the model with three layers: the leaf-nodes for detecting local contour fragments, the or-nodes specifying selection of leaf-nodes, and the root-node encoding the holistic distortion. In the training stage, for optimization of the And-Or tree learning, we extend the concave-convex procedure (CCCP) by embedding the structural clustering during the iterative learning steps. The inference of shape detection is consistent with the model optimization, which integrates the local testings via the leaf-nodes and or-nodes with the global verification via the root-node. The advantages of our approach are validated on the challenging shape databases (i.e., ETHZ and INRIA Horse) and summarized as follows. (1) The proposed method is able to accurately localize shape contours against unreliable edge detection and edge tracing. (2) The And-Or tree model enables us to well capture the intraclass variance. Liang Lin 0004, Xiaolong Wang 0004, Wei Yang 0019, Jian-Huang Lai	CVPR	2
2012	Dynamical And-Or Graph Learning for Object Shape Modeling and Detection abstract This paper studies a novel discriminative part-based model to represent and recognize object shapes with an “And-Or graph”. We define this model consisting of three layers: the leaf-nodes with collaborative edges for localizing local parts, the or-nodes specifying the switch of leaf-nodes, and the root-node encoding the global verification. A discriminative learning algorithm, extended from the CCCP [23], is proposed to train the model in a dynamical manner: the model structure (e.g., the configuration of the leaf-nodes associated with the or-nodes) is automatically determined with optimizing the multi-layer parameters during the iteration. The advantages of our method are two-fold. (i) The And-Or graph model enables us to handle well large intra-class variance and background clutters for object shape detection from images. (ii) The proposed learning algorithm is able to obtain the And-Or graph representation without requiring elaborate supervision and initialization. We validate the proposed method on several challenging databases (e.g., INRIA-Horse, ETHZ-Shape, and UIUC-People), and it outperforms the state-of-the-arts approaches. Xiaolong Wang 0004, Liang Lin 0004	NIPS	1
2011	Interactive CT image segmentation with online discriminative learning abstract Although interactive image segmentation has been widely exploited, current approaches present unsatisfactory results in medical image processing. This paper proposes a fast method for interactive CT image segmentation in which the tumor regions should be partitioned as foreground against the healthy tissues. In contrast to natural images, we have the following observation on CT images: (1) CT images often include discontinuous silhouette or cluttered spots caused by input de- vices or patient corporeity; (2) Disease areas often have varying appearance and shape. We thus train a discriminative fore- ground/background model based on user-placed scribbles. In our method, we extract positive and negative samples according to the foreground and background scribbles respectively, and use dense SIFT descriptors plus gray-level histogram as candidate features. With online learning, segmentation can be fast solved by the Bregman iteration. We test our method on CT liver images and demonstrate the advantage by comparing to state-of-the-art approaches. Wei Yang 0019, Xiaolong Wang 0004, Liang Lin 0004, Chengying Gao	ICIP	2