This paper introduces MobileH2R, a framework for learning generalizable vision-based human-to-mobile-robot (H2MR) handover skills. Unlike traditional fixed-base handovers, this task requires a mobile robot to reliably receive objects in a large workspace enabled by its mobility. Our key insight is that generalizable handover skills can be developed in simulators using high-quality synthetic data, without the need for real-world demonstrations. To achieve this, we propose a scalable pipeline for generating diverse synthetic full-body human motion data, an automated method for creating safe and imitation-friendly demonstrations, and an efficient 4D imitation learning method for distilling large-scale demonstrations into closed-loop policies with base-arm coordination. Experimental evaluations in both simulators and the real world show significant improvements (at least +15% success rate) over baseline methods in all cases. Experiments also validate that large-scale and diverse synthetic data greatly enhances robot learning, highlighting our scalable framework.

Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively after they occur and prevent foreseeable ones proactively. To this end, we propose Code-as-Monitor (CaM), a novel paradigm leveraging the vision-language model (VLM) for both open-set reactive and proactive failure detection. The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitoring. To enhance the accuracy and efficiency of monitoring, we further introduce constraint elements that abstract constraint-related entities or their parts into compact geometric elements. This approach offers greater generality, simplifies tracking, and facilitates constraint-aware visual programming by leveraging these elements as visual prompts. Experiments show that CaM achieves a 28.7% higher success rate and reduces execution time by 31.8% under severe disturbances compared to baselines across three simulators and a real-world setting. Moreover, CaM can be integrated with open-loop control policies to form closed-loop systems, enabling long-horizon tasks in cluttered scenes with dynamic environments. See the project page at https://zhoues.github.io/Code-as-Monitor.

As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models for human-like dexterous hands. In this paper, we introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions using single-view RGBD input. To accomplish this, we generate a dataset of 170 million dexterous grasp poses mapped to semantic parts across 174,000 objects in simulation, paired with detailed part-level captions. This large-scale dataset, named DexGraspNet 3.0, is used to train a VLM and flow-matching-based pose head capable of producing instruction-aligned grasp poses for tabletop objects. To assess DexVLG's performance, we create benchmarks in physics-based simulations and conduct real-world experiments. Extensive testing demonstrates DexVLG's strong zero-shot generalization capabilities-achieving over 76% zero-shot execution success rate and state-of-the-art part-grasp accuracy in simulation-and successful part-aligned grasps on physical objects in real-world scenarios.

Robotic dexterous grasping is important for interacting with the environment. To unleash the potential of data-driven models for dexterous grasping, a large-scale, highquality dataset is essential. While gradient-based optimization offers a promising way for constructing such datasets, previous works suffer from limitations, such as inefficiency, strong assumptions in the grasp quality energy, or limited object sets for experiments. Moreover, the lack of a standard benchmark for comparing different methods and datasets hinders progress in this field. To address these challenges, we develop a highly efficient synthesis system and a comprehensive benchmark with MuJoCo for dexterous grasping. We formulate grasp synthesis as a bilevel optimization problem, combining a novel lowerlevel quadratic programming (QP) with an upper-level gradient descent process. By leveraging recent advances in CUDAaccelerated robotic libraries and GPU-based QP solvers, our system can parallelize thousands of grasps and synthesize over 49 grasps per second on a single 3090 GPU. Our synthesized grasps for Shadow, Allegro, and Leap hands all achieve a success rate above 75 % in simulation, with a penetration depth under 1 mm, outperforming existing baselines on nearly all metrics. Compared to the previous large-scale dataset, DexGraspNet, our dataset significantly improves the performance of learning models, with a success rate from around 40 % to 80 % in simulation. Real-world testing of the trained model on the Shadow Hand achieves an 81 % success rate across 20 diverse objects. The codes and datasets are released on our project page: https://pku-epic.github.io/BODex.

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perception and pose detection. However, in real-world environments, these methods often face challenges due to imperfect depth perception, such as with transparent lids and reflective handles. Moreover, they generally lack the diversity in partbased interactions required for flexible and adaptable manipulation. To address these challenges, we introduced a largescale part-centric dataset for articulated object manipulation that features both photo-realistic material randomizations and detailed annotations of part-oriented, scene-level actionable interaction poses. We evaluated the effectiveness of our dataset by integrating it with several state-of-the-art methods for depth estimation and interaction pose prediction. Additionally, we proposed a novel modular framework that delivers superior and robust performance for generalizable articulated object manipulation. Our extensive experiments demonstrate that our dataset significantly improves the performance of depth perception and actionable interaction pose prediction in both simulation and real-world scenarios. More information and demos can be found at: https://pku-epic.github.io/GAPartManip/.

Articulated object manipulation poses a unique challenge compared to rigid object manipulation as the object itself represents a dynamic environment. In this work, we present a novel RL-based pipeline equipped with variable impedance control and motion adaptation leveraging observation history for generalizable articulated object manipulation, focusing on smooth and dexterous motion during zero-shot sim-to-real transfer (Fig. 1). To mitigate the sim-to-real gap, our pipeline diminishes reliance on vision by not leveraging the vision data feature (RGBD/pointcloud) directly as policy input but rather extracting useful low-dimensional data first via off-the-shelf modules. Additionally, we experience less sim-to-real gap by inferring object motion and its intrinsic properties via observation history as well as utilizing impedance control both in the simulation and in the real world. Furthermore, we develop a well-designed training setting with great randomization and a specialized reward system (task-aware and motion-aware) that enables multi-staged, end-to-end manipulation without heuristic motion planning. To the best of our knowledge, our policy is the first to report 84% success rate in the real world via extensive experiments with various unseen objects. Webpage: https://watch-less-feel-more.github.io/

Understanding and reasoning about the 4D space-time is crucial for Vision-and-Language Navigation (VLN). However, previous works lack in-depth exploration in this aspect, resulting in bottlenecked spatial perception and action precision of VLN agents. In this work, we introduce NaVid-4D, a Vision Language Model (VLM) based navigation agent taking the lead in explicitly showcasing the capabilities of spatial intelligence in the real world. Given natural language instructions, NaVid-4D requires only egocentric RGB-D video streams as observations to perform spatial understanding and reasoning for generating precise instruction-following robotic actions. NaVid-4D learns navigation policies using the data from simulation environments and is endowed with precise spatial understanding and reasoning capabilities using web data. Without the need to pre-train an RGB-D foundation model, we propose a method capable of directly injecting the depth features into the visual encoder of a VLM. We further compare the use of factually captured depth information with the monocularly estimated one and find NaVid-4D works well with both while using estimated depth offers greater gener-alization capability and better mitigates the sim-to-real gap. Extensive experiments demonstrate that NaVid-4D achieves state-of-the-art performance in simulation environment and makes impressive VLN performance with spatial intelligence happen in the real world.

Legged robots with advanced manipulation capabilities have the potential to significantly improve household duties and urban maintenance. Despite considerable progress in developing robust locomotion and precise manipulation methods, seamlessly integrating these into cohesive whole-body control for real-world applications remains challenging. In this paper, we present a modular framework for robust and generalizable whole-body loco-manipulation controller based on a single arm-mounted camera. By using reinforcement learning (RL), we enable a robust low-level policy for command execution over 5 dimensions (5D) and a grasp-aware high-level policy guided by a novel metric, Generalized Oriented Reachability Map (GORM). The proposed system achieves state-of-the-art one-time grasping accuracy of 89% in real world, including challenging tasks such as grasping transparent objects. Through extensive simulations and real-world experiments, we demonstrate that our system can effectively manage a large workspace, from floor level to above body height, and perform diverse whole-body loco-manipulation tasks. See our robot at work: quadwbg.github.io.

While spatial reasoning has made progress in object localization relationships, it often overlooks object orientation—a key factor in 6-DoF fine-grained manipulation. Traditional pose representations rely on pre-defined frames or templates, limiting generalization and semantic grounding. In this paper, we introduce the concept of semantic orientation, which defines object orientations using natural language in a reference-frame-free manner (e.g., the ''plug-in'' direction of a USB or the ''handle'' direction of a cup). To support this, we construct OrienText300K, a large-scale dataset of 3D objects annotated with semantic orientations, and develop PointSO, a general model for zero-shot semantic orientation prediction. By integrating semantic orientation into VLM agents, our SoFar framework enables 6-DoF spatial reasoning and generates robotic actions. Extensive experiments demonstrated the effectiveness and generalization of our SoFar, e.g., zero-shot 48.7\% successful rate on Open6DOR and zero-shot 74.9\% successful rate on SIMPLER-Env.

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information. To address these limitations, we propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling, thereby establishing a perception-prediction-action loop for manipulation tasks. Specifically, DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning. This design aligns with how humans interact with the world by first forming abstract multimodal reasoning chains before acting. To mitigate interference among the dynamic, spatial and semantic information during training, we adopt a block-wise structured attention mechanism that masks their mutual attention, preventing information leakage and keeping each representation clean and disentangled. Moreover, to model the conditional distribution over future actions, we employ a diffusion-based transformer that disentangles action representations from shared latent features. Extensive experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7 success rate on real robot tasks and 4.44 average length on the CALVIN ABC-D benchmarks.

Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. As a popular approach, probabilistic rotation modeling additionally carries prediction uncertainty information, compared to single-prediction rotation regression. For modeling probabilistic distribution over $\text{SO}(3)$SO(3), it is natural to use Gaussian-like Bingham distribution and matrix Fisher, however they are shown to be sensitive to outlier predictions, e.g., $180^\circ$180∘ error and thus are unlikely to converge with optimal performance. In this paper, we draw inspiration from multivariate Laplace distribution and propose a novel rotation Laplace distribution on $\text{SO}(3)$SO(3). Our rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region that it can improve. In addition, we show that our method also exhibits robustness to small noises and thus tolerates imperfect annotations. With this benefit, we demonstrate its advantages in semi-supervised rotation regression, where the pseudo labels are noisy. To further capture the multi-modal rotation solution space for symmetric objects, we extend our distribution to rotation Laplace mixture model and demonstrate its effectiveness. Our extensive experiments show that our proposed distribution and the mixture model achieve State-of-the-Art performance in all the rotation regression experiments over both probabilistic and non-probabilistic baselines.

Shape assembly composes complex shapes geometries by arranging simple part geometries and has wide applications in autonomous robotic assembly and CAD modeling. Existing works focus on geometry reasoning and neglect the actual physical assembly process of matching and fitting joints, which are the contact surfaces connecting different parts. In this paper, we consider contacting joints for the task of multi-part assembly. A successful joint-optimized assembly needs to satisfy the bilateral objectives of shape structure and joint alignment. We propose a hierarchical graph learning approach composed of two levels of graph representation learning. The part graph takes part geometries as input to build the desired shape structure. The joint-level graph uses part joints information and focuses on matching and aligning joints. The two kinds of information are combined to achieve the bilateral objectives. Extensive experiments demonstrate that our method outperforms previous methods, achieving better shape structure and higher joint alignment accuracy.

Open-vocabulary 3D instance segmentation is cuttingedge for its ability to segment 3D instances without prede-fined categories. However, progress in 3D lags behind its 2D counterpart due to limited annotated 3D data. To ad-dress this, recent works first generate 2D open-vocabulary masks through 2D models and then merge them into 3D instances based on metrics calculated between two neigh-boring frames. In contrast to these local metrics, we pro-pose a novel metric, view consensus rate, to enhance the utilization of multi-view observations. The key insight is that two 2D masks should be deemed part of the same 3D instance if a significant number of other 2D masks from different views contain both these two masks. Using this metric as edge weight, we construct a global mask graph where each mask is a node. Through iterative clustering of masks showing high view consensus, we generate a series of clusters, each representing a distinct 3D instance. Notably, our model is training-free. Through extensive ex-periments on publicly available datasets, including Scan-Net++, ScanNet200 and MatterPo rt3D, we demonstrate that our method achieves state-of-the-art performance in open-vocabulary 3D instance segmentation. Our project page is at https://pku-epic.github.ioIMaskClustering.

In this work, we present STOPNet, a framework for 6-DoF object suction detection on production lines, with a focus on but not limited to transparent objects, which is an important and challenging problem in robotic systems and modern industry. Current methods requiring depth input fail on transparent objects due to depth cameras’ deficiency in sensing their geometry, while we proposed a novel framework to reconstruct the scene on the production line depending only on RGB input, based on multiview stereo. Compared to existing works, our method not only reconstructs the whole 3D scene in order to obtain high-quality 6-DoF suction poses in real time but also generalizes to novel environments, novel arrangements and novel objects, including challenging transparent objects, both in simulation and the real world. Extensive experiments in simulation and the real world show that our method significantly surpasses the baselines and has better generalizability, which caters to practical industrial needs.

In this paper, we tackle the problem of grasping transparent and specular objects. This issue holds importance, yet it remains unsolved within the field of robotics due to failure of recover their accurate geometry by depth cameras. For the first time, we propose ASGrasp, a 6-DoF grasp detection network that uses an RGB-D active stereo camera. ASGrasp utilizes a two-layer learning-based stereo network for the purpose of transparent object reconstruction, enabling material-agnostic object grasping in cluttered environments. In contrast to existing RGB-D based grasp detection methods, which heavily depend on depth restoration networks and the quality of depth maps generated by depth cameras, our system distinguishes itself by its ability to directly utilize raw IR and RGB images for transparent object geometry reconstruction. We create an extensive synthetic dataset through domain randomization, which is based on GraspNet-1Billion. Our experiments demonstrate that ASGrasp can achieve over 90% success rate for generalizable transparent object grasping in both simulation and the real via seamless sim-to-real transfer. Our method significantly outperforms SOTA networks and even surpasses the performance upper bound set by perfect visible point cloud inputs. Project page: https://pku-epic.github.io/ASGrasp

Mobile manipulation constitutes a fundamental task for robotic assistants and garners significant attention within the robotics community. A critical challenge inherent in mobile manipulation is the effective observation of the target while approaching it for grasping. In this work, we propose a graspability-aware mobile manipulation approach powered by an online grasping pose fusion framework that enables a temporally consistent grasping observation. Specifically, the predicted grasping poses are online organized to eliminate the redundant, outlier grasping poses, which can be encoded as a grasping pose observation state for reinforcement learning. Moreover, on-the-fly fusing the grasping poses enables a direct assessment of graspability, encompassing both the quantity and quality of grasping poses. This assessment can subsequently serve as an observe-to-grasp reward, motivating the agent to prioritize actions that yield detailed observations while approaching the target object for grasping. Through extensive experiments conducted on the Habitat and Isaac Gym simulators, we find that our method attains a good balance between observation and manipulation, yielding high performance under various grasping metrics. Furthermore, we discover that the incorporation of temporal information from grasping poses aids in mitigating the sim-to-real gap, leading to robust performance in challenging real-world experiments. Project page: https://pku-epic.github.io/GAMMA/

This work tackles the problem of task-oriented dexterous hand pose synthesis, which involves generating a static hand pose capable of applying a task-specific set of wrenches to manipulate objects. Unlike previous approaches that focus solely on force-closure grasps, which are unsuitable for non-prehensile manipulation tasks (e.g., turning a knob or pressing a button), we introduce a unified framework covering force-closure grasps, non-force-closure grasps, and a variety of non-prehensile poses. Our key idea is a novel optimization objective quantifying the disparity between the Task Wrench Space (TWS, the desired wrenches predefined as a task prior) and the Grasp Wrench Space (GWS, the achievable wrenches computed from the current hand pose). By minimizing this objective, gradient-based optimization algorithms can synthe-size task-oriented hand poses without additional human demonstrations. Our specific contributions include 1) a fast, accurate, and differentiable technique for estimating the GWS boundary; 2) a task-oriented objective function based on the disparity between the estimated GWS boundary and the provided TWS boundary; and 3) an efficient implementation of the synthesis pipeline that leverages CUDA accelerations and supports large-scale parallelization. Experimental results on 10 diverse tasks demonstrate a 72.6% success rate in simulation. Furthermore, real-world validation for 4 tasks confirms the effectiveness of synthesized poses for manipulation. Notably, despite being primarily tailored for task-oriented hand pose synthesis, our pipeline can generate force-closure grasps 50 times faster than DexGraspNet while maintaining comparable grasp quality. Project page: https://pku-epic.github.io/TaskDexGrasp/.

The integration of large-scale Vision-Language Models (VLMs) with embodied AI can greatly enhance the generalizability and the capacity to follow open instructions for robots. However, existing studies on object manipulation are not up to full consideration of the 6-DoF requirements, let alone establishing a comprehensive benchmark. In this paper, we propel the pioneer construction of the benchmark and approach for Open-instruction 6-DoF Object Rearrangement (Open6DOR). Specifically, we collect a synthetic dataset of 200+ objects and carefully design 5400+ Open6DOR tasks. These tasks are divided into the Position-track, Rotation-track, and 6-DoF-track for evaluating different embodied agents in predicting the positions and rotations of target objects.Besides, we also propose a VLM-based approach for Open6DOR, named Open6DOR-GPT, which empowers GPT-4V with 3D-awareness and simulation-assistance while exploiting its strengths in generalizability and instruction-following. We compare the existing embodied agents with our Open6DOR-GPT on the proposed Open6DOR benchmark and find that Open6DOR-GPT achieves the state-of-the-art performance. We further show the impressive performance of Open6DOR-GPT in diverse real-world experiments.

In this work, we tackle the challenging task of jointly tracking hand object poses and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0. We for the first time propose a point cloud-based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion. Our HandTrackNet proposes a novel hand pose canonicalization module to ease the tracking task, yielding accurate and robust hand joint tracking. Our pipeline then reconstructs the full hand via converting the predicted hand joints into a MANO hand. For object tracking, we devise a simple yet effective module that estimates the object SDF from the first frame and performs optimization-based tracking. Finally, a joint optimization step is adopted to perform joint hand and object reasoning, which alleviates the occlusion-induced ambiguity and further refines the hand pose. During training, the whole pipeline only sees purely synthetic data, which are synthesized with sufficient variations and by depth simulation for the ease of generalization. The whole pipeline is pertinent to the generalization gaps and thus directly transferable to real in-the-wild data. We evaluate our method on two real hand object interaction datasets, e.g. HO3D and DexYCB, without any fine-tuning. Our experiments demonstrate that the proposed method significantly outperforms the previous state-of-the-art depth-based hand and object pose estimation and tracking methods, running at a frame rate of 9 FPS. We have released our code on https://github.com/PKU-EPIC/HOTrack.

The task of Vision-Language Navigation (VLN) is for an embodied agent to reach the global goal according to the instruction. Essentially, during navigation, a series of sub-goals need to be adaptively set and achieved, which is naturally a hierarchical navigation process. However, previous methods leverage a single-step planning scheme, i.e., directly performing navigation action at each step, which is unsuitable for such a hierarchical navigation process. In this paper, we propose an Adaptive Zone-aware Hierarchical Planner (AZHP) to explicitly divides the navigation process into two heterogeneous phases, i.e., sub-goal setting via zone partition/selection (high-level action) and sub-goal executing (low-level action), for hierarchical planning. Specifically, AZHP asynchronously performs two levels of action via the designed State-Switcher Module (SSM). For high-level action, we devise a Scene-aware adaptive Zone Partition (SZP) method to adaptively divide the whole navigation area into different zones on-the-fly. Then the Goal-oriented Zone Selection (GZS) method is proposed to select a proper zone for the current sub-goal. For low-level action, the agent conducts navigation-decision multi-steps in the selected zone. Moreover, we design a Hierarchical RL (HRL) strategy and auxiliary losses with curriculum learning to train the AZHP framework, which provides effective supervision signals for each stage. Extensive experiments demonstrate the superiority of our proposed method, which achieves state-of-the-art performance on three VLN benchmarks (REVERIE, SOON, R2R).

Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category object manipulation. In this work, we build the first large-scale, part-based cross-category object manipulation benchmark, PartManip, which is composed of 11 object categories, 494 objects, and 1432 tasks in 6 task classes. Compared to previous work, our benchmark is also more diverse and realistic, i.e., having more objects and using sparse-view point cloud as input without oracle information like part segmentation. To tackle the difficulties of vision-based policy learning, we first train a statebased expert with our proposed part-based canonicalization and part-aware rewards, and then distill the knowledge to a vision-based student. We also find an expressive backbone is essential to overcome the large diversity of different objects. For cross-category generalization, we introduce domain adversarial learning for domain-invariant feature extraction. Extensive experiments in simulation show that our learned policy can outperform other methods by a large margin, especially on unseen object categories. We also demonstrate our method can successfully manipulate novel objects in the real world. Our benchmark has been released in https://pku-epic.github.io/PartManip.

For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via Generalizable and Actionable Parts (GAParts). By identifying and defining 9 GAPart classes (lids, handles, etc.) in 27 object categories, we construct a large-scale part-centric interactive dataset, GAPartNet, where we provide rich, part-level annotations (semantics, poses) for 8,489 part instances on 1,166 objects. Based on GAPartNet, we investigate three cross-category tasks: part segmentation, part pose estimation, and partbased object manipulation. Given the significant domain gaps between seen and unseen object categories, we propose a robust 3D segmentation method from the perspective of domain generalization by integrating adversarial learning techniques. Our method outperforms all existing methods by a large margin, no matter on seen or unseen categories. Furthermore, with part segmentation and pose estimation results, we leverage the GAPart pose definition to design part-based manipulation heuristics that can generalize well to unseen object categories in both the simulator and the real world.

Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data. Rotation, as an important quantity in computer vision, graphics, and robotics, can exhibit many ambiguities when occlusion and symmetry occur and thus demands such probabilistic models. Though much progress has been made for NFs in Euclidean space, there are no effective normalizing flows without discontinuity or many-to-one mapping tailored for SO(3) manifold. Given the unique non-Euclidean properties of the rotation manifold, adapting the existing NFs to SO(3) manifold is non-trivial. In this paper, we propose a novel normalizing flow on SO (3) by combining a Mobius transformation-based coupling layer and a quaternion affine transformation. With our proposed rotation normalizing flows, one can not only effectively express arbitrary distributions on SO(3), but also conditionally build the target distribution given input observations. Extensive experiments show that our rotation normalizing flows significantly outperform the baselines on both unconditional and conditional tasks.

Domain adaptive semantic segmentation methods commonly utilize stage-wise training, consisting of a warm-up and a self-training stage. However, this popular approach still faces several challenges in each stage: for warm-up, the widely adopted adversarial training often results in limited performance gain, due to blind feature alignment; for self-training, finding proper categorical thresholds is very tricky. To alleviate these issues, we first propose to replace the adversarial training in the warm-up stage by a novel symmetric knowledge distillation module that only accesses the source domain data and makes the model domain generalizable. Surprisingly, this domain generalizable warm-up model brings substantial performance improvement, which can be further amplified via our proposed cross-domain mixture data augmentation technique. Then, for the self-training stage, we propose a threshold-free dynamic pseudo-label selection mechanism to ease the aforementioned threshold problem and make the model better adapted to the target domain. Extensive experiments demonstrate that our framework achieves remarkable and consistent improvements compared to the prior arts on popular benchmarks. Codes and models are available at https://github.com/fy-visionIDiGA

In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by successful pipelines used in parallel gripper grasping, we split the task into two stages: 1) grasp proposal (pose) generation and 2) goal-conditioned grasp execution. For the first stage, we propose a novel probabilistic model of grasp pose conditioned on the point cloud observation that factorizes rotation from translation and articulation. Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud. For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution. Note that it is very challenging to learn this highly generalizable grasp policy that only takes realistic inputs without oracle states. We thus propose several important innovations, including state canonicalization, object curriculum, and teacher-student distillation. In-tegrating the two stages, our final pipeline becomes the first to achieve universal generalization for dexterous grasping, demonstrating an average success rate of more than 60% on thousands of object instances, which significantly out-performs all baselines, meanwhile showing only a minimal generalization gap.

Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D space, a 3D-aware agent can advance its ObjectNav capability via learning from fine-grained spatial information. However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost. In this work, we propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation. Through extensive experiments, we show that this framework can dramatically improve the performance in ObjectNav through learning from 3D scene representation. Our framework achieves the best performance among all modular-based methods on the Matterport3D and Gibson datasets, while requiring (up to 30x) less computational cost for training. The code will be released to benefit the community.11Homepage: https://pku-epic.github.io/3D-Aware-ObjectNav/

Fine-grained capture of 3D Human-Object Interactions (HOIs) enhances human activity comprehension and supports various downstream visual tasks. However, previous models often assume that humans interact with rigid objects using only a few body parts, constraining their applicability. In this paper, we address the intricate challenge of Full-Body Articulated Human-Object Interaction (f-AHOI), where complete human bodies interact with articulated objects having interconnected movable joints. We introduce CHAIRS, an extensive motion-captured f-AHOI dataset comprising 17.3 hours of diverse interactions involving 46 participants and 81 articulated as well as rigid sittable objects. The CHAIRS provides 3D meshes of both humans and articulated objects throughout the interactive sequences, offering realistic and physically plausible full-body interactions. We demonstrate the utility of CHAIRS through object pose estimation. Leveraging the geometric relationships inherent in HOI, we propose a pioneering model that employs human pose estimation to address articulated object pose and shape estimation within whole-body interactions. Given an image and an estimated human pose, our model reconstructs the object’s pose and shape, refining the reconstruction based on a learned interaction prior. Across two evaluation scenarios, our model significantly outperforms baseline methods. Additionally, we showcase the significance of CHAIRS in a downstream task involving human pose generation conditioned on interacting with articulated objects. We anticipate that the availability of CHAIRS will advance the community’s understanding of finer-grained interactions.

We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity. Previous mesh generative models either have difficulties in depicting a diverse data space from only a few examples or fail to ensure physical validity of their samples. Regarding the above challenges, we propose two key innovations, including 1) a hierarchical mesh deformation-based generative model based upon the divide-and-conquer philosophy to alleviate the few-shot challenge by borrowing transferrable deformation patterns from large scale rigid meshes and 2) a physics-aware deformation correction scheme to encourage physically plausible generations. We conduct extensive experiments on 6 articulated categories to demonstrate the superiority of our method in generating articulated meshes with better diversity, higher visual fidelity, and better physical validity over previous methods in the few-shot setting. Further, we validate solid contributions of our two innovations in the ablation study. Project page with code is available at meowuu7.github.io/few-arti-obj-gen.

We propose a novel, object-agnostic method for learning a universal policy for dexterous object grasping from realistic point cloud observations and proprioceptive information under a table-top setting, namely UniDexGrasp++. To address the challenge of learning the vision-based policy across thousands of object instances, we propose Geometry-aware Curriculum Learning (GeoCurriculum) and Geometry-aware iterative Generalist-Specialist Learning (GiGSL) which leverage the geometry feature of the task and significantly improve the generalizability. With our proposed techniques, our final policy shows universal dexterous grasping on thousands of object instances with 85.4% and 78.2% success rate on the train set and test set which outperforms the state-of-the-art baseline UniDexGrasp by 11.7% and 11.3%, respectively.

In this work, we tackle 6-DoF grasp detection for transparent and specular objects, which is an important yet challenging problem in vision-based robotic systems, due to the failure of depth cameras in sensing their geometry. We, for the first time, propose a multiview RGB-based 6-DoF grasp detection network, GraspNeRF, that leverages the generalizable neural radiance field (NeRF) to achieve material-agnostic object grasping in clutter. Compared to the existing NeRF-based 3-DoF grasp detection methods that rely on densely captured input images and time-consuming per-scene optimization, our system can perform zero-shot NeRF construction with sparse RGB inputs and reliably detect 6-DoF grasps, both in real-time. The proposed framework jointly learns generalizable NeRF and grasp detection in an end-to-end manner, optimizing the scene representation construction for the grasping. For training data, we generate a large-scale photorealistic domain-randomized synthetic dataset of grasping in cluttered tabletop scenes that enables direct transfer to the real world. Our extensive experiments in synthetic and real-world environments demonstrate that our method significantly outperforms all the baselines in all the experiments while remaining in real-time. Project page can be found at https://pku-epic.github.io/GraspNeRF.

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology. However, dexterous grasping is much more under-explored than object grasping with parallel grippers, partially due to the lack of a large-scale dataset. In this work, we present a large-scale robotic dexterous grasp dataset, DexGraspNet, generated by our proposed highly efficient synthesis method that can be generally applied to any dexterous hand. Our method leverages a deeply accelerated differentiable force closure estimator and thus can efficiently and robustly synthesize stable and diverse grasps on a large scale. We choose ShadowHand and generate 1.32 million grasps for 5355 objects, covering more than 133 object categories and containing more than 200 diverse grasps for each object instance, with all grasps having been validated by the Isaac Gym simulator. Compared to the previous dataset from Liu et al. generated by GraspIt!, our dataset has not only more objects and grasps, but also higher diversity and quality. Via performing cross-dataset experiments, we show that training several algorithms of dexterous grasp synthesis on our dataset significantly outperforms training on the previous one. To access our data and code, including code for human and Allegro grasp synthesis, please visit our project page: https://pku-epic.github.io/DexGraspNet/.

Due to the lack of training labels and the difficulty of annotating, dealing with adverse driving conditions such as nighttime has posed a huge challenge to the perception system of autonomous vehicles. Therefore, adapting knowledge from a labelled daytime domain to an unlabelled nighttime domain has been widely researched. In addition to labelled daytime datasets, existing nighttime datasets usually provide nighttime images with corresponding daytime reference images captured at nearby locations for reference. The key challenge is to minimize the performance gap between the two domains. In this paper, we propose LoopDA for domain adaptive nighttime semantic segmentation. It consists of self-loops that result in reconstructing the input data using predicted semantic maps, by rendering them into the encoded features. In a warm-up training stage, the self-loops comprise of an inner-loop and an outer-loop, which are responsible for intra-domain refinement and inter-domain alignment, respectively. To reduce the impact of day-night pose shifts, in the later self-training stage, we propose a co-teaching pipeline that involves an offline pseudo-supervision signal and an online reference-guided signal ‘DNA’ (Day-Night Agreement), bringing substantial benefits to enhance nighttime segmentation. Our model outperforms prior methods on Dark Zurich and Nighttime Driving datasets for semantic segmentation. Code and pretrained models are available at https://github.com/fyvision/LoopDA.

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation - multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either flexibility with a single neural map or scalability due to extra storage of feature grids, we propose a pure neural representation tackling both difficulties with a divide-and-conquer design. In our method, neural submaps are incrementally allocated alongside the scanning trajectory and efficiently learned with local neural bundle adjustments. The submaps can be refined individually in a back-end optimization and optimized jointly to realize submap-level loop closure. Meanwhile, we propose a hybrid tracking approach combining randomized and gradient-based pose optimizations. For the first time, randomized optimization is made possible in neural tracking with several key designs to the learning process, enabling efficient and robust tracking even under fast camera motions. The extensive evaluation demonstrates that our method attains higher reconstruction quality than the state of the arts for large-scale scenes and under fast camera motions.

High-dimensional nonlinear state estimation is at the heart of inertial-aided navigation systems (INS). Traditional methods usually rely on good initialization and find difficulty in handling large interframe transformations due to fast camera motion. We opt to tackle these challenges by solving the depth inertial odometry (DIO) problem with random optimization. To address the exponentially increased amount of candidate states sampled for the high-dimensional state space, we propose a highly efficient variant of random optimization based on the idea of active subspace. Our method identifies the active dimensions, which contribute most significantly to the decrease of the cost function in each iteration, and samples candidate states only within the corresponding subspace. This allows us to efficiently explore the 18D state space of DIO and achieve good optimality by sampling and evaluating only thousands of candidate states. Experiments show that our method attains highly robust and accurate DIO under fast camera motions and low light conditions, without needing a slow-motion warm-up for initialization.

Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network learning in both forward and backward passes. While several works have proposed different regression-friendly rotation representations, very few works have been devoted to improving the gradient back-propagating in the backward pass. In this paper, we propose a manifold-aware gradient that directly backpropagates into deep network weights. Leveraging Riemannian optimization to construct a novel projective gradient, our proposed regularized projective manifold gradient (RPMG) method helps networks achieve new state-of-the-art performance in a variety of rotation estimation tasks. Our proposed gradient layer can also be applied to other smooth manifolds such as the unit sphere. Our project page is at https://jychen18.github.io/RPMG.

We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences col-lected by 9 participants interacting with 800 different ob-ject instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to pro-mote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud se-quences, category-level object pose tracking, and egocen-tric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces huge research opportunities.

We describe a method to deal with performance drop in semantic segmentation caused by viewpoint changes within multi-camera systems, where temporally paired images are readily available, but the annotations may only be abundant for a few typical views. Existing methods alleviate performance drop via domain alignment in a shared space and assume that the mapping from the aligned space to the output is transferable. However, the novel content induced by viewpoint changes may nullify such a space for effective alignments, thus resulting in negative adaptation. Our method works without aligning any statistics of the images between the two domains. Instead, it utilizes a novel attention-based view transformation network trained only on color images to hallucinate the semantic images for the target. Despite the lack of supervision, the view transformation network can still generalize to semantic images thanks to the induced “information transport” bias. Furthermore, to resolve ambiguities in converting the semantic images to semantic labels, we treat the view transformation network as a functional representation of an unknown mapping implied by the color images and propose functional label hallucination to generate pseudo-labels with uncertainties in the target domains. Our method surpasses baselines built on state-of-the-art correspondence estimation and view synthesis methods. Moreover, it outperforms the state-of-the-art unsupervised domain adaptation methods that utilize self-training and adversarial domain alignments. Our code and dataset will be made publicly available.

As a popular geometric representation, point clouds have attracted much attention in 3D vision, leading to many applications in autonomous driving and robotics. One important yet unsolved issue for learning on point cloud is that point clouds of the same object can have significant geometric variations if generated using different procedures or captured using different sensors. These inconsistencies induce domain gaps such that neural networks trained on one domain may fail to generalize on others. A typical technique to reduce the domain gap is to perform adversarial training so that point clouds in the feature space can align. However, adversarial training is easy to fall into degenerated local minima, resulting in negative adaptation gains. Here we propose a simple yet effective method for unsupervised domain adaptation on point clouds by employing a self-supervised task of learning geometry-aware implicits, which plays two critical roles in one shot. First, the geometric information in the point clouds is preserved through the implicit representations for downstream tasks. More importantly, the domain-specific variations can be effectively learned away in the implicit space. We also propose an adaptive strategy to compute unsigned distance fields for arbitrary point clouds due to the lack of shape models in practice. When combined with a task loss, the proposed outperforms state-of-the-art unsupervised domain adaptation methods that rely on adversarial domain alignment and more complicated self-supervised tasks. Our method is evaluated on both PointDA-10 and GraspNet datasets. Code and data are available at: https://github.com/Jhonve/ImplicitPCDA.

We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps. The key to this problem lies in the goal position estimation to enable more efficient robot movements. Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction. In this paper, we propose a novel algorithm, namely NeuralCoMapping, which takes advantage of both approaches. We reduce the problem to bipartite graph matching, which establishes the node correspondences between two graphs, denoting robots and frontiers. We introduce a multiplex graph neural network (mGNN) that learns the neural distance to fill the affinity matrix for more effective graph matching. We optimize the mGNN with a differentiable linear assignment layer by maximizing the long-term values that favor time efficiency and map completeness via reinforcement learning. We compare our algorithm with several state-of-the-art multi-robot active mapping approaches and adapted reinforcement-learning baselines. Experimental results demonstrate the superior performance and exceptional generalization ability of our algorithm on various indoor scenes and unseen number of robots, when only trained with 9 indoor scenes.

Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. Recent works achieve good performance relying on a large amount of expensive-to-obtain labeled data. To reduce the amount of supervision, we for the first time propose a general framework, FisherMatch, for semi-supervised rotation regression, without assuming any domain-specific knowledge or paired data. Inspired by the popular semi-supervised approach, FixMatch, we propose to leverage pseudo label filtering to facilitate the information flow from labeled data to unlabeled data in a teacher-student mutual learning framework. However, incorporating the pseudo label filtering mechanism into semi-supervised rotation regression is highly non-trivial, mainly due to the lack of a reliable confidence measure for rotation prediction. In this work, we propose to leverage matrix Fisher distribution to build a probabilistic model of rotation and devise a matrix Fisher-based regressor for jointly predicting rotation along with its prediction uncertainty. We then propose to use the entropy of the predicted distribution as a confidence measure, which enables us to perform pseudo label filtering for rotation regression. For supervising such distribution-like pseudo labels, we further investigate the problem of how to enforce loss between two matrix Fisher distributions. Our extensive experiments show that our method can work well even under very low labeled data ratios on different benchmarks, achieving significant and consistent performance improvement over supervised learning and other semi-supervised learning baselines. Our project page is at https://yd-yin.github.io/FisherMatch.

Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training techniques. When applying to 3D tasks, the irregular data structure and limited data scale add to the difficulty of transformer's application. We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers. On the one hand, we propose the codebook-based attention that projects an attention space into its subspace represented by the combination of “prototypes” in a learnable codebook. It regularizes attention learning and improves generalization. On the other hand, we propose geometry-aware self-attention that utilizes geometric information (geometric pattern, density) to guide attention learning. CodedVTR could be embedded into existing sparse convolution-based methods, and bring consistent performance improvements for indoor and outdoor 3D semantic segmentation tasks.

3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection applicable to both indoor and outdoor scenes. We leverage a teacher-student mutual learning framework to propagate information from the labeled to the unlabeled train set in the form of pseudo-labels. However, due to the high task complexity, we observe that the pseudo-labels suffer from significant noise and are thus not directly usable. To that end, we introduce a confidence-based filtering mechanism, inspired by FixMatch. We set confidence thresholds based upon the predicted objectness and class probability to filter low-quality pseudo-labels. While effective, we observe that these two measures do not sufficiently capture localization quality. We therefore propose to use the estimated 3D IoU as a localization metric and set category-aware self-adjusted thresholds to filter poorly localized proposals. We adopt VoteNet as our backbone detector on indoor datasets while we use PV-RCNN on the autonomous driving dataset, KITTI. Our method consistently improves state-of-the-art methods on both ScanNet and SUN-RGBD benchmarks by significant margins under all label ratios (including fully labeled setting). For example, when training using only 10% labeled data on ScanNet, 3DIoUMatch achieves 7.7 absolute improvement on [email protected] and 8.5 absolute improvement on [email protected] upon the prior art. On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1.8% to 7.6% under different label ratio and categories.

Localizing the camera in a known indoor environment is a key building block for scene mapping, robot navigation, AR, etc. Recent advances estimate the camera pose via optimization over the 2D/3D-3D correspondences established between the coordinates in 2D/3D camera space and 3D world space. Such a mapping is estimated with either a convolution neural network or a decision tree using only the static input image sequence, which makes these approaches vulnerable to dynamic indoor environments that are quite common yet challenging in the real world. To address the aforementioned issues, in this paper, we propose a novel outlier-aware neural tree which bridges the two worlds, deep learning and decision tree approaches. It builds on three important blocks: (a) a hierarchical space partition over the indoor scene to construct the decision tree; (b) a neural routing function, implemented as a deep classification network, employed for better 3D scene understanding; and (c) an outlier rejection module used to filter out dynamic points during the hierarchical routing process. Our proposed algorithm is evaluated on the RIO-10 benchmark developed for camera relocalization in dynamic indoor environments. It achieves robust neural routing through space partitions and outperforms the state-of-the-art approaches by around 30% on camera pose accuracy, while running comparably fast for evaluation.

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts; and (ii) obtaining robust motion-based rigid body segmentation applicable to novel object categories. We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds. Code at https://github.com/huangjh-pub/multibody-sync.

In this work, we tackle the problem of single image-based 3D shape retrieval (IBSR), where we seek to find the most matched shape of a given single 2D image from a shape repository. Most of the existing works learn to embed 2D images and 3D shapes into a common feature space and perform metric learning using a triplet loss. Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning. We note that adopting such cross-modal contrastive learning between 2D images and 3D shapes into IBSR tasks is non-trivial and challenging: contrastive learning requires very strong data augmentation in constructed positive pairs to learn the feature invariance, whereas traditional metric learning works do not have this requirement. Moreover, object shape and appearance are entangled in 2D query images, thus making the learning task more difficult than contrasting single-modal data. To mitigate the challenges, we propose to use multi-view grayscale rendered images from the 3D shapes as a shape representation. We then introduce a strong data augmentation technique based on color transfer, which can significantly but naturally change the appearance of the query image, effectively satisfying the need for contrastive learning. Finally, we propose to incorporate a novel category-level contrastive loss that helps distinguish similar objects from different categories, in addition to classic instance-level contrastive loss. Our experiments demonstrate that our approach achieves the best performance on all the three popular IBSR benchmarks, including Pix3D, Stanford Cars, and Comp Cars, outperforming the previous state-of-the-art from 4% - 15% on retrieval accuracy.

In this work, we tackle the problem of category-level online pose tracking of objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pose. Our pipeline is composed of three modules: 1) a pose canonicalization module that normalizes the pose of the input depth point cloud; 2) RotationNet, a module that directly regresses small interframe delta rotations; and 3) CoordinateNet, a module that predicts the normalized coordinates and segmentation, enabling analytical computation of the 3D size and translation. Leveraging the small pose regime in the pose-canonicalized point clouds, our method integrates the best of both worlds by combining dense coordinate prediction and direct rotation regression, thus yielding an end-to-end differentiable pipeline optimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Our extensive experiments demonstrate that our method achieves new state-of-the-art performance on category-level rigid object pose (NOCSREAL275 [29]) and articulated object pose benchmarks (SAPIEN [34], BMVC [18]) at the fastest FPS ∼ 12.

Category-level object pose estimation aims to find 6D object poses of previously unseen object instances from known categories without access to object CAD models. To reduce the huge amount of pose annotations needed for category-level learning, we propose for the first time a self-supervised learning framework to estimate category-level 6D object pose from single 3D point clouds. During training, our method assumes no ground-truth pose annotations, no CAD models, and no multi-view supervision. The key to our method is to disentangle shape and pose through an invariant shape reconstruction module and an equivariant pose estimation module, empowered by SE(3) equivariant point cloud networks. The invariant shape reconstruction module learns to perform aligned reconstructions, yielding a category-level reference frame without using any annotations. In addition, the equivariant pose estimation module achieves category-level pose estimation accuracy that is comparable to some fully supervised methods. Extensive experiments demonstrate the effectiveness of our approach on both complete and partial depth point clouds from the ModelNet40 benchmark, and on real depth point clouds from the NOCS-REAL 275 dataset. The project page with code and visualizations can be found at: dragonlong.github.io/equi-pose.

This paper addresses the task of category-level pose estimation for articulated objects from a single depth image. We present a novel category-level approach that correctly accommodates object instances previously unseen during training. We introduce Articulation-aware Normalized Coordinate Space Hierarchy (ANCSH) - a canonical representation for different articulated objects in a given category. As the key to achieve intra-category generalization, the representation constructs a canonical object space as well as a set of canonical part spaces. The canonical object space normalizes the object orientation, scales and articulations (e.g. joint parameters and states) while each canonical part space further normalizes its part pose and scale. We develop a deep network based on PointNet++ that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space. By leveraging the canonicalized joints, we demonstrate: 1) improved performance in part pose and scale estimations using the induced kinematic constraints from joints; 2) high accuracy for joint parameter estimation in camera space.

Building home assistant robots has long been a goal for vision and robotics researchers. To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable. Existing environments achieve these requirements for robotics simulation with different levels of simplification and focus. We take one step further in constructing an environment that supports household tasks for training robot learning algorithm. Our work, SAPIEN, is a realistic and physics-rich simulated environment that hosts a large-scale set of articulated objects. SAPIEN enables various robotic vision and interaction tasks that require detailed part-level understanding.We evaluate state-of-the-art vision algorithms for part detection and motion attribute recognition as well as demonstrate robotic interaction tasks using heuristic approaches and reinforcement learning algorithms. We hope that SAPIEN will open research directions yet to be explored, including learning cognition through interaction, part motion discovery, and construction of robotics-ready simulated game environment.

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics of 3D objects on a plane that have just been subjected to an impulsive force. In particular, we predict the changes in state-3D position, rotation, velocities, and stability. Different from previous work, our approach can generalize dynamics predictions to object shapes and initial conditions that were unseen during training. Our method takes the 3D object's shape as a point cloud and its initial linear and angular velocities as input. We extract shape features and use a recurrent neural network to predict the full change in state at each time step. Our model can support training with data from both a physics engine or the real world. Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level'' 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)-a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, greatly reducing proposals with low objectness.

Abstract Creating dynamic virtual environments consisting of humans interacting with objects is a fundamental problem in computer graphics. While it is well‐accepted that agent interactions play an essential role in synthesizing such scenes, most extant techniques exclusively focus on static scenes, leaving the dynamic component out. In this paper, we present a generative model to synthesize plausible multi‐step dynamic human‐object interactions. Generating multi‐step interactions is challenging since the space of such interactions is exponential in the number of objects, activities, and time steps. We propose to handle this combinatorial complexity by learning a lower dimensional space of plausible human‐object interactions. We use action plots to represent interactions as a sequence of discrete actions along with the participating objects and their states. To build action plots, we present an automatic method that uses state‐of‐the‐art computer vision techniques on RGB videos in order to detect individual objects and their states, extract the involved hands, and recognize the actions performed. The action plots are built from observing videos of everyday activities and are used to train a generative model based on a Recurrent Neural Network (RNN). The network learns the causal dependencies and constraints between individual actions and can be used to generate novel and diverse multi‐step human‐object interactions. Our representation and generative model allows new capabilities in a variety of applications such as interaction prediction, animation synthesis, and motion planning for a real robotic agent.