With the rapid advancements in diffusion models and 3D generation techniques, dynamic 3D content generation has become a crucial research area. However, achieving high-fidelity 4D (dynamic 3D) generation with strong spatial-temporal consistency remains a challenging task. Inspired by recent findings that pretrained diffusion features capture rich correspondences, we propose FB-4D, a novel 4D generation framework that integrates a Feature Bank mechanism to enhance both spatial and temporal consistency in generated frames. In FB-4D, we store features extracted from previous frames and fuse them into the process of generating subsequent frames, ensuring consistent characteristics across both time and multiple views. To ensure a compact representation, the Feature Bank is updated by a proposed dynamic merging mechanism. Leveraging this Feature Bank, we demonstrate for the first time that generating additional reference sequences through multiple autoregressive iterations can continuously improve generation performance. Experimental results show that FB-4D significantly outperforms existing methods in terms of rendering quality, spatial-temporal consistency, and robustness. It surpasses all multi-view generation tuning-free approaches by a large margin and achieves performance on par with training-based methods. Our code and data will be publicly available to support future research.

We introduce GaussianAvatar-Editor, an innovative framework for text-driven editing of animatable Gaussian head avatars that can be fully controlled in expression, pose, and viewpoint. Unlike static 3D Gaussian editing, editing animatable 4D Gaussian avatars presents challenges related to motion occlusion and spatial-temporal inconsistency. To address these issues, we propose the Weighted Alpha Blending Equation (WABE). This function enhances the blending weight of visible Gaussians while suppressing the influence on non-visible Gaussians, effectively handling motion occlusion during editing. Furthermore, to improve editing quality and ensure 4D consistency, we incorporate conditional adversarial learning into the editing process. This strategy helps to refine the edited results and maintain consistency throughout the animation. By integrating these methods, our GaussianAvatar-Editor

We focus on the human-humanoid interaction problem optionally with an object. We propose a new task named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The previous work only focuses on human interaction without objects and generates body reactions without hand. Besides, they also do not consider the task as an online setting, which means the reactor can only see the current information and cannot perceive the future actions of the actor. To support the task of online full-body motion reaction synthesis, we construct two datasets named HHI and CoChair and propose a unified method. Specifically, we encode the motion of human actors and objects from an interactioncentric view through a social affordance representation. Then we leverage a social affordance forecasting scheme to enable the reactor to predict based on the imagined future. We also use SE(3)-Equivariant Neural Networks to learn the local frame to canonicalize the social affordance. Experiments demonstrate that our approach effectively generates high-quality reactions on HHI and CoChair. Furthermore, we also validate our method on existing human interaction datasets Interhuman and Chi3D in real-time at 25 fps. Website: https://yunzeliu.github.io/iHuman/

As interest grows in world models that predict future states from current observations and actions, accurately modeling part-level dynamics has become increasingly relevant for various applications. Existing approaches, such as Puppet-Master, rely on fine-tuning large-scale pre-trained video diffusion models, which are impractical for real-world use due to the limitations of 2D video representation and slow processing times. To overcome these challenges, we present PartRM, a novel 4D reconstruction framework that simultaneously models appearance, geometry, and part-level motion from multi-view images of a static object. PartRM builds upon large 3D Gaussian reconstruction models, leveraging their extensive knowledge of appearance and geometry in static objects. To address data scarcity in 4D, we introduce the PartDrag-4D dataset, providing multi-view observations of part-level dynamics across over 20,000 states. We enhance the model’s understanding of interaction conditions with a multi-scale drag embedding module that captures dynamics at varying granularities. To prevent catastrophic forgetting during fine-tuning, we implement a two-stage training process that focuses sequentially on motion and appearance learning. Experimental results show that PartRM establishes a new state-of-the-art in part-level motion learning and can be applied in manipulation tasks in robotics. Our code, data, and models are publicly available to facilitate future research.

Existing motion generation methods based on MoCap data are often limited by data quality and coverage. In this work, we propose a framework that generates diverse, physically feasible full-body human reaching and grasping motions using only brief walking MoCap data. Based on the observation that walking data captures valuable movement patterns transferable across tasks and, on the other hand, the advanced kinematic methods can generate diverse grasping poses, which can then be interpolated into motions to serve as task-specific guidance. Our approach incorporates an active data generation strategy to maximize the utility of the generated motions, along with a local feature alignment mechanism that transfers natural movement patterns from walking data to enhance both the success rate and naturalness of the synthesized motions. By combining the fidelity and stability of natural walking with the flexibility and generalizability of task-specific generated data, our method demonstrates strong performance and robust adaptability in diverse scenes and with unseen objects.

Hybrid Mamba-Transformer networks have recently garnered broad attention. These networks can leverage the scalability of Transformers while capitalizing on Mamba’s strengths in long-context modeling and computational efficiency. However, the challenge of effectively pretraining such hybrid networks remains an open question. Existing methods, such as Masked Autoencoders (MAE) or autoregressive (AR) pretraining, primarily focus on single-type network architectures. In contrast, pretraining strategies for hybrid architectures must be effective for both Mamba and Transformer components. Based on this, we propose Masked Autoregressive Pretraining (MAP) to pretrain a hybrid MambaTransformer vision backbone network. This strategy combines the strengths of both MAE and Autoregressive pretraining, improving the performance of Mamba and Transformer modules within a unified paradigm. Experimental results show that the hybrid Mamba-Transformer vision backbone network pretrained with MAP significantly outperforms other pretraining strategies, achieving state-of-the-art performance. We validate the method’s effectiveness on both 2D and 3D datasets and provide detailed ablation studies to support the design choices for each component. Code and checkpoints are available at https://github.com/yunzeliu/MAP.

Understanding how humans cooperatively rearrange household objects is critical for VR/AR and human-robot interaction. However, in-depth studies on modeling these behaviors are under-researched due to the lack of relevant datasets. We fill this gap by presenting CORE4D, a novel large-scale 4D human-object-human interaction dataset focusing on collaborative object rearrangement, which encompasses diverse compositions of various object geometries, collaboration modes, and 3D scenes. With 1K human-object-human motion sequences captured in the real world, we enrich CORE4D by contributing an iterative collaboration retargeting strategy to augment motions to a variety of novel objects. Leveraging this approach, CORE4D comprises a total of 11K collaboration sequences spanning 3K real and virtual object shapes. Benefiting from extensive motion patterns provided by CORE4D, we benchmark two tasks aiming at generating human-object interaction: human-object motion forecasting and interaction synthesis. Extensive experiments demonstrate the effectiveness of our collaboration retargeting strategy and indicate that CORE4D has posed new challenges to existing human-object interaction generation methodologies.

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.

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.

We address the challenge of developing a generalizable neural tracking controller for dexterous manipulation from human references. This controller aims to manage a dexterous robot hand to manipulate diverse objects for various purposes defined by kinematic human-object interactions. Developing such a controller is complicated by the intricate contact dynamics of dexterous manipulation and the need for adaptivity, generalizability, and robustness. Current reinforcement learning and trajectory optimization methods often fall short due to their dependence on task-specific rewards or precise system models. We introduce an approach that curates large-scale successful robot tracking demonstrations, comprising pairs of human references and robot actions, to train a neural controller. Utilizing a data flywheel, we iteratively enhance the controller's performance, as well as the number and quality of successful tracking demonstrations. We exploit available tracking demonstrations and carefully integrate reinforcement learning and imitation learning to boost the controller's performance in dynamic environments. At the same time, to obtain high-quality tracking demonstrations, we individually optimize per-trajectory tracking by leveraging the learned tracking controller in a homotopy optimization method. The homotopy optimization, mimicking chain-of-thought, aids in solving challenging trajectory tracking problems to increase demonstration diversity. We showcase our success by training a generalizable neural controller and evaluating it in both simulation and real world. Our method achieves over a 10% improvement in success rates compared to leading baselines. The project website with animated results is available at [DexTrack](https://meowuu7.github.io/DexTrack/).

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to misalignment and increased complexity. In contrast, VILA-U employs a single autoregressive next-token prediction framework for both tasks, eliminating the need for additional components like diffusion models. This approach not only simplifies the model but also achieves near state-of-the-art performance in visual language understanding and generation. The success of VILA-U is attributed to two main factors: the unified vision tower that aligns discrete visual tokens with textual inputs during pretraining, which enhances visual perception, and autoregressive image generation can achieve similar quality as diffusion models with high-quality dataset. This allows VILA-U to perform comparably to more complex models using a fully token-based autoregressive framework.

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.

We propose a self-supervised approach for 3D dynamic reconstruction of articulated motions based on Generative Adversarial Networks and Neural Radiance Fields. Our method reconstructs articulated objects and recover their continuous motions and attributes from an unordered, discontinuous image set. Notably, we treat motion states as time-independent, recognizing that articulated objects can exhibit identical motions at different times. The key insight of our approach utilizes generative adversarial networks to create a continuous implicit motion state space. Initially, we employ a motion network extracts discrete motion states from images as anchors. These anchors are then expanded across the latent space using generative adversarial networks. Subsequently, motion state latent codes are input into motion-aware neural radiance fields for dynamic appearance and geometry reconstruction. To deduce motion attributes from the continuously generated motions, we adopt a cluster-based strategy. We thoroughly evaluate and validate our method on both synthesized and real data, demonstrating superior fidelity in appearances, geometries, and motion attributes of articulated objects compared to state-of-the-art methods.

We present GenN2N, a unified NeRF-to-NeRF translation framework for various NeRF translation tasks such as text-driven NeRF editing, colorization, super-resolution, in-painting, etc. Unlike previous methods designed for individual translation tasks with task-specific schemes, GenN2N achieves all these NeRF editing tasks by employing a plug-and-play image-to-image translator to perform editing in the 2D domain and lifting 2D edits into the 3D NeRF space. Since the 3D consistency of 2D edits may not be assured, we propose to model the distribution of the underlying 3D edits through a generative model that can cover all possible edited NeRFs. To model the distribution of 3D edited NeRFs from 2D edited images, we carefully design a VAE-GAN that encodes images while decoding NeRFs. The latent space is trained to align with a Gaussian distribution and the NeRFs are supervised through an adversarial loss on its renderings. To ensure the latent code does not depend on 2D viewpoints but truly reflects the 3D edits, we also regularize the latent code through a contrastive learning scheme. Extensive experiments on various editing tasks show GenN2N, as a universal framework, performs as well or better than task-specific specialists while possessing flexible generative power. More results on our project page: https://xiangyueliu.github.io/GenN2N/.

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. To rapidly expand the data scale, we present a fully automatic data acquisition pipeline combining multi-view sensing with an optical motion capture system. With the vast research fields provided by TACO, we benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis. Extensive experiments re-veal new insights, challenges, and opportunities for advancing the studies of generalizable hand-object motion anal-ysis and synthesis. Our data and code are available at https://taco2024.github.io.

The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.

This paper presents GenH2R, a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in various complex trajectories. We acquire such generalizability by learning H2R handover at scale with a comprehensive solution including procedural simulation assets creation, automated demonstration generation, and effective imitation learning. We leverage large-scale 3D model repositories, dexterous grasp generation methods, and curve-based 3D animation to create an H2R handover simulation environment named GenH2R-Sim, surpassing the number of scenes in existing simulators by three orders of magnitude. We further introduce a distillation-friendly demonstration generation method that automati-cally generates a million high-quality demonstrations suitable for learning. Finally, we present a 4D imitation learning method augmented by a future forecasting objective to distill demonstrations into a visuo-motor handover policy. Experimental evaluations in both simulators and the real world demonstrate significant improvements (at least +10% success rate) over baselines in all cases.

This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DreamLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DreamLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DreamLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DreamLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: https://dreamllm.github.io.

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data scarcity and challenges in label acquisition. To address these issues, we propose a self-supervised learning method that leverages the cross-modal relationship between point cloud videos and image videos to acquire meaningful feature representations. Intra-modal and cross-modal contrastive learning techniques are employed to facilitate effective comprehension of point cloud video. We also propose a multi-level contrastive approach for both modalities. Through extensive experiments, we demonstrate that our method significantly surpasses previous state-of-the-art approaches, and we conduct comprehensive ablation studies to validate the effectiveness of our proposed designs.

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.

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not all pixels are equal, skipping computations for less-important regions offers a simple and effective measure to reduce the computation. This, however, is hard to be translated into actual speedup for CNNs since it breaks the regularity of the dense convolution workload. In this paper, we introduce SparseViT that revisits activation sparsity for recent window-based vision transformers (ViTs). As window attentions are naturally batched over blocks, actual speedup with window activation pruning becomes possible: i.e., ~50% latency reduction with 60% sparsity. Different layers should be assigned with different pruning ratios due to their diverse sensitivities and computational costs. We introduce sparsity-aware adaptation and apply the evolutionary search to efficiently find the optimal layerwise sparsity configuration within the vast search space. SparseViT achieves speedups of 1.5×, 1.4×, and 1.3× compared to its dense counterpart in monocular 3D object detection, 2D instance segmentation, and 2D semantic segmentation, respectively, with negligible to no loss of accuracy.

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.

Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a challenging task and the lack of large scale labeled data also constrain the performance of deep learning based approaches. In this paper, we tackle the task of object kinematic motion prediction problem in a semi-weakly supervised manner. Our key observations are two-fold. First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale. Second, semantic part segmentation and mobile part segmentation is not always consistent but it is possible to detect the mobile parts from the underlying 3D structure. Towards this end, we propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters, which are further refined based on geometric alignment. This network can be first trained on PartNet-Mobility dataset with fully labeled mobility information and then applied on PartNet dataset with fine-grained and hierarchical part-level segmentation. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information and can further be used for weakly-supervised learning with pre-existing segmentation. Our experiments show there are significant performance boosts with the augmented data for previous method designed for kinematic motion prediction on 3D partial scans.

We propose a method that trains a neural radiance field (NeRF) to encode not only the appearance of the scene but also semantic correlations between scene points, regions, or entities - aiming to capture their mutual co-variation patterns. In contrast to the traditional first-order photometric reconstruction objective, our method explicitly regularizes the learning dynamics to align the Jacobians of highly-correlated entities, which proves to maximize the mutual information between them under random scene perturbations. By paying attention to this second-order information, we can shape a NeRF to express semantically meaningful synergies when the network weights are changed by a delta along the gradient of a single entity, region, or even a point. To demonstrate the merit of this mutual information modeling, we leverage the coordinated behavior of scene entities that emerges from our shaping to perform label propagation for semantic and instance segmentation. Our experiments show that a JacobiNeRF is more efficient in propagating annotations among 2D pixels and 3D points compared to NeRFs without mutual information shaping, especially in extremely sparse label regimes - thus reducing annotation burden. The same machinery can further be used for entity selection or scene modifications. Our code is available at https://github.com/xxm19/jacobinerf.

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.

Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. To overcome such issues, this paper proposes a new 4D self-supervised pretraining method called Complete-to-Partial 4D Distillation. Our key idea is to formulate 4D self-supervised representation learning as a teacher-student knowledge distillation framework and let the student learn useful 4D representations with the guidance of the teacher. Experiments show that this approach significantly outperforms previous pre-training approaches on a wide range of 4D point cloud sequence understanding tasks. Code is available at: https://github.com/dongyh20/C2P.

In this work, we focus on a novel task of category-level functional hand-object manipulation synthesis covering both rigid and articulated object categories. Given an object geometry, an initial human hand pose as well as a sparse control sequence of object poses, our goal is to generate a physically reasonable hand-object manipulation sequence that performs like human beings. To address such a challenge, we first design CAnonicalized Manipulation Spaces (CAMS), a two-level space hierarchy that canonicalizes the hand poses in an object-centric and contact-centric view. Benefiting from the representation capability of CAMS, we then present a two-stage framework for synthesizing human-like manipulation animations. Our framework achieves state-of-the-art performance for both rigid and articulated categories with impressive visual effects. Codes and video results can be found at our project homepage: https://cams-hoi.github.io/

We focus on learning descriptive geometry and motion features from 4D point cloud sequences in this work. Existing works usually develop generic 4D learning tools without leveraging the prior that a 4D sequence comes from a single 3D scene with local dynamics. Based on this observation, we propose to learn region-wise coordinate frames that transform together with the underlying geometry. With such frames, we can factorize geometry and motion to facilitate a feature-space geometric reconstruction for more effective 4D learning. To learn such region frames, we develop a rotation equivariant network with a frame stabilization strategy. To leverage such frames for better spatial-temporal feature learning, we develop a frame-guided 4D learning scheme. Experiments show that this approach significantly outperforms previous state-of-the-art methods on a wide range of 4D understanding benchmarks.

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.

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting temporal consistency. To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information. However, the direct application of the Transporter to 3D point clouds is infeasible due to their structural differences from 2D images. Thus, we propose the first 3D version of the Transporter, which leverages hybrid 3D representation, cross attention, and implicit reconstruction. We apply this new learning system on 3D articulated objects and non-rigid animals (humans and rodents) and show that learned keypoints are spatio-temporally consistent. Additionally, we propose a closed-loop control strategy that utilizes the learned keypoints for 3D object manipulation and demonstrate its superior performance. Codes are available at https://github.com/zhongcl-thu/3D-Implicit-Transporter.

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms have different characteristics: (i) contrastive models are data-hungry that suffer from a representation over-fitting issue; (ii) generative models have a data filling issue that shows inferior data scaling capacity compared to contrastive models. This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose contrast with reconstruct (ReCon) that unifies these two paradigms. ReCon is trained to learn from both generative modeling teachers and cross-modal contrastive teachers through ensemble distillation, where the generative student is used to guide the contrastive student. An encoder-decoder style ReCon-block is proposed that transfers knowledge through cross attention with stop-gradient, which avoids pretraining over-fitting and pattern difference issues. ReCon achieves a new state-of-the-art in 3D representation learning, e.g., 91.26% accuracy on ScanObjectNN. Codes have been released at https://github.com/qizekun/ReCon.

Transparent objects are common in daily life. However, depth sensing for transparent objects remains a challenging problem. While learning-based methods can leverage shape priors to improve the sensing quality, the labor-intensive data collection in real world and the sim-to-real domain gap restrict these methods' scalability. In this paper, we propose a method to finetune a stereo network with sparse depth labels automatically collected using a probing system with tactile feedback. We present a novel utility function to evaluate the benefit of touches. By approximating and optimizing the utility function, we can optimize the probing locations given a fixed touching budget to better improve the network's performance on real objects. We further combine tactile depth supervision with a confidence-based regularization to prevent over-fitting during finetuning. To evaluate the effectiveness of our method, we construct a real-world dataset including both diffuse and transparent objects. Experimental results on this dataset show that our method can significantly improve real-world depth sensing accuracy, especially for transparent objects.

We present a novel vectorized indoor modeling approach that converts point clouds into building information models (BIM) with concise and semantically segmented polygonal meshes. Existing methods detect planar shapes and connect them to complete the scene. Some focus on floor plan reconstruction as a simplified problem to better analyze connectivity between planes of floors and walls. However, the connectivity analysis is still challenging and ill-posed with incomplete point clouds as input. We propose ArrangementNet to estimate scene arrangements from an incomplete point cloud, which we can easily convert into a BIM model. ArrangementNet is a novel graph neural network that consumes noisy over-partitioned initial arrangements extracted through non-learning techniques and outputs high-quality scene arrangement. The core of ArrangementNet is an extended graph convolution that leverages co-linear and co-face relationships in the arrangement and improves the quality of prediction in complex scenes. We apply ArrangementNet to improve floor plan and ceiling arrangements and enrich them with semantic objects as scene arrangements for scene generation. Our approach faithfully models challenging scenes obtained from laser scans or multiview stereo and shows significant improvement in BIM model reconstruction compared to the state-of-the-art. Our code is available at https://github.com/zssjh/ArrangementNet.

This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to the physical interactions between the object and the user. Given a malfunctional object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. Inspired by this, we propose FixIt, a dataset that contains about 5k poorly-designed 3D physical objects paired with choices to fix them. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics. Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix. Experimental results show that our framework outperforms baseline models by a large margin, and can generalize well to objects with similar interaction types. Code and dataset are publicly available11http://fixing-malfunctional.csail.mit.edu.

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.

Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications. To tackle this problem, some works design task-specific solutions by translating human understanding of the task to machine's learning process, which faces the risk of missing the optimal strategy since machines do not necessarily understand in the exact human way. Others try to use conventional task-agnostic approaches designed for domain generalization problems with no task prior knowledge considered. To solve the above issues, we propose AutoGPart, a generic method enabling training generalizable 3D part segmentation networks with the task prior considered. AutoGPart builds a supervision space with geometric prior knowledge encoded, and lets the machine to search for the optimal supervisions from the space for a specific segmentation task automatically. Extensive experiments on three generalizable 3D part segmentation tasks are conducted to demonstrate the effectiveness and versatility of AutoGPart. We demonstrate that the performance of segmentation networks using simple backbones can be significantly improved when trained with supervisions searched by our method.

Rigged puppets are one of the most prevalent representations to create 2D character animations. Creating these puppets requires partitioning characters into independently moving parts. In this work, we present a method to automatically identify such articulated parts from a small set of character poses shown in a sprite sheet, which is an illustration of the character that artists often draw before puppet creation. Our method is trained to infer articulated parts, e.g. head, torso and limbs, that can be reassembled to best reconstruct the given poses. Our results demonstrate significantly better performance than alternatives qualitatively and quantitatively. Our project page https://zhan-xu.github.io/parts/ includes our code and data.

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.

Rotation equivariance has recently become a strongly desired property in the 3D deep learning community. Yet most existing methods focus on equivariance regarding a global input rotation while ignoring the fact that rotation symmetry has its own spatial support. Specifically, we consider the object detection problem in 3D scenes, where an object bounding box should be equivariant regarding the object pose, independent of the scene motion. This suggests a new desired property we call object-level rotation equivariance. To incorporate object-level rotation equivariance into 3D object detectors, we need a mechanism to extract equivariant features with local object-level spatial support while being able to model cross-object context information. To this end, we propose Equivariant Object detection Network (EON) with a rotation equivariance suspension design to achieve object-level equivariance. EON can be applied to modern point cloud object detectors, such as VoteNet and PointR-CNN, enabling them to exploit object rotation symmetry in scene-scale inputs. Our experiments on both indoor scene and autonomous driving datasets show that significant improvements are obtained by plugging our EON design into existing state-of-the-art 3D object detectors. Project website: https://kovenyu.com/EON/

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.

We present MoRig, a method that automatically rigs character meshes driven by single-view point cloud streams capturing the motion of performing characters. Our method is also able to animate the 3D meshes according to the captured point cloud motion. MoRig’s neural network encodes motion cues from the point clouds into features that are informative about the articulated parts of the performing character. These motion-aware features guide the inference of an appropriate skeletal rig for the input mesh, which is then animated based on the point cloud motion. Our method can rig and animate diverse characters, including humanoids, quadrupeds, and toys with varying articulation. It accounts for occluded regions in the point clouds and mismatches in the part proportions between the input mesh and captured character. Compared to other rigging approaches that ignore motion cues, MoRig produces more accurate rigs, well-suited for re-targeting motion from captured characters.

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 study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors. Based on the observation that sparse 3D point clouds are sampled from 3D surfaces, we take a Complete and Label approach to recover the underlying surfaces before passing them to a segmentation network. Specifically, we design a Sparse Voxel Completion Network (SVCN) to complete the 3D surfaces of a sparse point cloud. Unlike semantic labels, to obtain training pairs for SVCN requires no manual labeling. We also introduce local adversarial learning to model the surface prior. The recovered 3D surfaces serve as a canonical domain, from which semantic labels can transfer across different LiDAR sensors. Experiments and ablation studies with our new benchmark for cross-domain semantic labeling of LiDAR data show that the proposed approach provides 6.3-37.6% better performance than previous domain adaptation methods.

This paper proposes a method for representation learning of multimodal data using contrastive losses. A traditional approach is to contrast different modalities to learn the information shared among them. However, that approach could fail to learn the complementary synergies between modalities that might be useful for downstream tasks. Another approach is to concatenate all the modalities into a tuple and then contrast positive and negative tuple correspondences. However, that approach could consider only the stronger modalities while ignoring the weaker ones. To address these issues, we propose a novel contrastive learning objective, TupleInfoNCE. It contrasts tuples based not only on positive and negative correspondences, but also by composing new negative tuples using modalities describing different scenes. Training with these additional negatives encourages the learning model to examine the correspondences among modalities in the same tuple, ensuring that weak modalities are not ignored. We provide a theoretical justification based on mutual-information for why this approach works, and we propose a sample optimization algorithm to generate positive and negative samples to maximize training efficacy. We find that TupleInfoNCE significantly outperforms previous state of the arts on three different downstream tasks.

A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts and relations, thus playing an important role in the interpretation and organization of visual signals as well as for the generalization of visual perception and reasoning. However, existing visual reasoning benchmarks mostly focus on objects rather than parts. Visual reasoning based on the full part-whole hierarchy is much more challenging than object-centric reasoning due to finer-grained concepts, richer geometry relations, and more complex physics. Therefore, to better serve for part-based conceptual, relational and physical reasoning, we introduce a new large-scale diagnostic visual reasoning dataset named PTR. PTR contains around 80k RGBD synthetic images with ground truth object and part level annotations regarding semantic instance segmentation, color attributes, spatial and geometric relationships, and certain physical properties such as stability. These images are paired with 800k machine-generated questions covering various types of reasoning types, making them a good testbed for visual reasoning models. We examine several state-of-the-art visual reasoning models on this dataset and observe that they still make many surprising mistakes in situations where humans can easily infer the correct answer. We believe this dataset will open up new opportunities for part-based reasoning. PTR dataset and baseline models are publicly available.

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.

We introduce AdaCoSeg, a deep neural network architecture for adaptive co-segmentation of a set of 3D shapes represented as point clouds. Differently from the familiar single-instance segmentation problem, co-segmentation is intrinsically contextual: how a shape is segmented can vary depending on the set it is in. Hence, our network features an adaptive learning module to produce a consistent shape segmentation which adapts to a set. Specifically, given an input set of unsegmented shapes, we first employ an offline pre-trained part prior network to propose per-shape parts. Then the co-segmentation network iteratively and jointly optimizes the part labelings across the set subjected to a novel group consistency loss defined by matrix ranks. While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaSeg is a consistent part labeling for the input set, with each shape segmented into up to (a user-specified) K parts. Overall, our method is weakly supervised, producing segmentations tailored to the test set, without consistent ground-truth segmentations. We show qualitative and quantitative results from AdaSeg and evaluate it via ablation studies and comparisons to state-of-the-art co-segmentation methods.

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.

Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and for many other applications in 3D content creation. The common approach of encoding shapes as points in a high-dimensional latent feature space suggests treating shape differences as vectors in that space. Instead, we treat shape differences as primary objects in their own right and propose to encode them in their own latent space. In a setting where the shapes themselves are encoded in terms of fine-grained part hierarchies, we demonstrate that a separate encoding of shape deltas or differences provides a principled way to deal with inhomogeneities in the shape space due to different combinatorial part structures, while also allowing for compactness in the representation, as well as edit abstraction and transfer. Our approach is based on a conditional variational autoencoder for encoding and decoding shape deltas, conditioned on a source shape. We demonstrate the effectiveness and robustness of our approach in multiple shape modification and generation tasks, and provide comparison and ablation studies on the PartNet dataset, one of the largest publicly available 3D datasets.

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.

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds. To demonstrate the applicability of learned geodesic-aware representations, we propose fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis. Our method improves the state-of-the-art on multiple representative tasks that can benefit from understandings of the underlying surface topology, including point upsampling, normal estimation, mesh reconstruction and non-rigid shape classification.

We introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps). The key idea is to utilize a 4-rotational symmetric(4-RoSy) field to define a domain for convolution on a surface. Though 4-RoSy fields have several properties favor-able for convolution on surfaces (low distortion, few singularities, consistent parameterization, etc.), orientations are ambiguous up to 4-fold rotation at any sample point. So, we introduce a new convolutional operator invariant to the4-RoSy ambiguity and use it in a network to extract features from high-resolution signals on geodesic neighborhoods of a surface. In comparison to alternatives, such as PointNet-based methods which lack a notion of orientation, the coherent structure given by these neighborhoods results in significantly stronger features. As an example application, we demonstrate the benefits of our architecture for 3D semantic segmentation of textured 3D meshes. The results show that our method outperforms all existing methods on the basis of mean IoU by a significant margin in both geometry-only(6.4%) and RGB+Geometry (6.9-8.2%) settings.

Fitting geometric primitives to 3D point cloud data bridges a gap between low-level digitized 3D data and high-level structural information on the underlying 3D shapes. As such, it enables many downstream applications in 3D data processing. For a long time, RANSAC-based methods have been the gold standard for such primitive fitting problems, but they require careful per-input parameter tuning and thus do not scale well for large datasets with diverse shapes. In this work, we introduce Supervised Primitive Fitting Network (SPFN), an end-to-end neural network that can robustly detect a varying number of primitives at different scales without any user control. The network is supervised using ground truth primitive surfaces and primitive membership for the input points. Instead of directly predicting the primitives, our architecture first predicts per-point properties and then uses a differential model estimation module to compute the primitive type and parameters. We evaluate our approach on a novel benchmark of ANSI 3D mechanical component models and demonstrate a significant improvement over both the state-of-the-art RANSAC-based methods and the direct neural prediction.

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a baseline method for part instance segmentation and demonstrate its superior performance over existing methods.

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.

The ability to generate novel, diverse, and realistic 3D shapes along with associated part semantics and structure is central to many applications requiring high-quality 3D assets or large volumes of realistic training data. A key challenge towards this goal is how to accommodate diverse shape variations, including both continuous deformations of parts as well as structural or discrete alterations which add to, remove from, or modify the shape constituents and compositional structure. Such object structure can typically be organized into a hierarchy of constituent object parts and relationships, represented as a hierarchy of n -ary graphs. We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n -ary graphs, (ii) can be robustly trained on large and complex shape families, and (iii) be used to generate a great diversity of realistic structured shape geometries. Technically, we accomplish this by drawing inspiration from recent advances in graph neural networks to propose an order-invariant encoding of n -ary graphs, considering jointly both part geometry and inter-part relations during network training. We extensively evaluate the quality of the learned latent spaces for various shape families and show significant advantages over baseline and competing methods. The learned latent spaces enable several structure-aware geometry processing applications, including shape generation and interpolation, shape editing, or shape structure discovery directly from un-annotated images, point clouds, or partial scans.

Important high-level vision tasks require rich semantic descriptions of objects at part level. Based upon previous work on part localization, in this paper, we address the problem of inferring rich semantics imparted by an object part in still images. Specifically, we propose to tokenize the semantic space as a discrete set of part states. Our modeling of part state is spatially localized, therefore, we formulate the part state inference problem as a pixel-wise annotation problem. An iterative part-state inference neural network that is efficient in time and accurate in performance is specifically designed for this task. Extensive experiments demonstrate that the proposed method can effectively predict the semantic states of parts and simultaneously improve part segmentation, thus benefiting a number of visual understanding applications. The other contribution of this paper is our part state dataset which contains rich part-level semantic annotations.

Object functionality is often expressed through part articulation - as when the two rigid parts of a scissor pivot against each other to perform the cutting function. Such articulations are often similar across objects within the same functional category. In this paper we explore how the observation of different articulation states provides evidence for part structure and motion of 3D objects. Our method takes as input a pair of unsegmented shapes representing two different articulation states of two functionally related objects, and induces their common parts along with their underlying rigid motion. This is a challenging setting, as we assume no prior shape structure, no prior shape category information, no consistent shape orientation, the articulation states may belong to objects of different geometry, plus we allow inputs to be noisy and partial scans, or point clouds lifted from RGB images. Our method learns a neural network architecture with three modules that respectively propose correspondences, estimate 3D deformation flows, and perform segmentation. To achieve optimal performance, our architecture alternates between correspondence, deformation flow, and segmentation prediction iteratively in an ICP-like fashion. Our results demonstrate that our method significantly outperforms state-of-the-art techniques in the task of discovering articulated parts of objects. In addition, our part induction is object-class agnostic and successfully generalizes to new and unseen objects.

In this paper, we study the problem of semantic annotation on 3D models that are represented as shape graphs. A functional view is taken to represent localized information on graphs, so that annotations such as part segment or keypoint are nothing but 0-1 indicator vertex functions. Compared with images that are 2D grids, shape graphs are irregular and non-isomorphic data structures. To enable the prediction of vertex functions on them by convolutional neural networks, we resort to spectral CNN method that enables weight sharing by parametrizing kernels in the spectral domain spanned by graph Laplacian eigenbases. Under this setting, our network, named SyncSpecCNN, strives to overcome two key challenges: how to share coefficients and conduct multi-scale analysis in different parts of the graph for a single shape, and how to share information across related but different shapes that may be represented by very different graphs. Towards these goals, we introduce a spectral parametrization of dilated convolutional kernels and a spectral transformer network. Experimentally we tested SyncSpecCNN on various tasks, including 3D shape part segmentation and keypoint prediction. State-of-the-art performance has been achieved on all benchmark datasets.

Few prior works study deep learning on point sets. PointNet is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

We propose a method for converting geometric shapes into hierarchically segmented parts with part labels. Our key idea is to train category-specific models from the scene graphs and part names that accompany 3D shapes in public repositories. These freely-available annotations represent an enormous, untapped source of information on geometry. However, because the models and corresponding scene graphs are created by a wide range of modelers with different levels of expertise, modeling tools, and objectives, these models have very inconsistent segmentations and hierarchies with sparse and noisy textual tags. Our method involves two analysis steps. First, we perform a joint optimization to simultaneously cluster and label parts in the database while also inferring a canonical tag dictionary and part hierarchy. We then use this labeled data to train a method for hierarchical segmentation and labeling of new 3D shapes. We demonstrate that our method can mine complex information, detecting hierarchies in man-made objects and their constituent parts, obtaining finer scale details than existing alternatives. We also show that, by performing domain transfer using a few supervised examples, our technique outperforms fully-supervised techniques that require hundreds of manually-labeled models.

Large repositories of 3D shapes provide valuable input for data-driven analysis and modeling tools. They are especially powerful once annotated with semantic information such as salient regions and functional parts. We propose a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations. Given a shape collection and a user-specified region label our goal is to correctly demarcate the corresponding regions with minimal manual work. Our active framework achieves this goal by cycling between manually annotating the regions, automatically propagating these annotations across the rest of the shapes, manually verifying both human and automatic annotations, and learning from the verification results to improve the automatic propagation algorithm. We use a unified utility function that explicitly models the time cost of human input across all steps of our method. This allows us to jointly optimize for the set of models to annotate and for the set of models to verify based on the predicted impact of these actions on the human efficiency. We demonstrate that incorporating verification of all produced labelings within this unified objective improves both accuracy and efficiency of the active learning procedure. We automatically propagate human labels across a dynamic shape network using a conditional random field (CRF) framework, taking advantage of global shape-to-shape similarities, local feature similarities, and point-to-point correspondences. By combining these diverse cues we achieve higher accuracy than existing alternatives. We validate our framework on existing benchmarks demonstrating it to be significantly more efficient at using human input compared to previous techniques. We further validate its efficiency and robustness by annotating a massive shape dataset, labeling over 93,000 shape parts, across multiple model classes, and providing a labeled part collection more than one order of magnitude larger than existing ones.

In this letter, we present a new algorithm for a single image super-resolution using the analysis sparse prior in thelαβ color space. Experimental results show that our algorithm outperforms other existing state-of-the-art methods. In addition, due to the high scalability of our algorithm, key modules of the proposed algorithm can be integrated with other super resolution algorithms.