三维重建（十四）——铰接类文章整理

文章目录

• Awesome Articulated Objects Understanding
• • Table of contents
  • 一、Survey
  • • 1. Survey on Modeling of Articulated Objects
  • Articulation Detection
  • • 1. RoSI: Recovering 3D Shape Interiors from Few Articulation Images
    • 2. Understanding 3D Object Interaction from a Single Image
    • 3. OPDMulti: Openable Part Detection for Multiple Objects
    • 4. OPD: Single-view 3D Openable Part Detection
    • 5. Understanding 3D Object Articulation in Internet Videos
    • 6. A Hand Motion-guided Articulation and Segmentation Estimation
    • 7. Camera-to-Robot Pose Estimation from a Single Image
    • 8. Deep Part Induction from Articulated Object Pairs
  • Articulation Estimation
  • • 1. CAPT: Category-level Articulation Estimation from a Single Point Cloud Using Transformer
    • 2. MARS: Multimodal Active Robotic Sensing for Articulated Characterization
    • 3. OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation
    • 4. Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds
    • 5. Category-Level Articulated Object 9D Pose Estimation via Reinforcement Learning
    • 6. Towards Real-World Category-level Articulation Pose Estimation
    • 7. Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
    • 8. Distributional Depth-Based Estimation of Object Articulation Models
    • 9. ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory
    • 10. Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimation
    • 11. Category-Level Articulated Object Pose Estimation
    • 12. RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud
    • 13. Learning to Generalize Kinematic Models to Novel Objects
  • Dataset
  • • 1. RoCap: A Robotic Data Collection Pipeline for the Pose Estimation of Appearance-Changing Objects
    • 2. ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
    • 3. AO-Grasp: Articulated Object Grasp Generation
    • 4. MultiScan: Scalable RGBD scanning for 3D environments with articulated objects
    • 5. AKB-48: A real-world articulated object knowledge base
    • 6. SAPIEN: A simulated part-based interactive environment
    • 7. Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
    • 8. The RBO Dataset of Articulated Objects and Interactions
    • 9. 3D Shape Segmentation with Projective Convolutional Networks
  • Dataset Augmentation
  • • 1. S2O: Static to Openable Enhancement for Articulated 3D Objects
    • 2. Semi-Weakly Supervised Object Kinematic Motion Prediction
  • Digital Twins
  • • 1. URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images
    • 2. Real2Code: Reconstruct Articulated Objects via Code Generation
    • 3. RoboStudio: A Physics Consistent World Model for Robotic Arm with Hybrid Representation
    • 4. DexSim2Real2: Building Explicit World Model for Precise Articulated Object Dexterous Manipulation
    • 5. ACDC: Automated Creation of Digital Cousins for Robust Policy Learning
    • 6. Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
    • 7. PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
    • 8. Building Digital Twins of Articulated Objects and Scenes through Interactive Perception
  • Generation
  • • 1. Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
    • 2. Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics
    • 3. PhysPart: Physically Plausible Part Completion for Interactable Objects
    • 4. SINGAPO: Single Image Controlled Generation of Articulated Parts in Object
    • 5. NAP: Neural 3D Articulation Prior
    • 6. CAGE: Controllable Articulation Generation
  • Implicit Representation
  • • 1. SM${}^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects
    • 2. Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects
    • 3. Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects
    • 4. REACTO: Reconstructing Articulated Objects from a Single Video
    • 5. Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
    • 6. NARF24: Estimating Articulated Object Structure for Implicit Rendering
    • 7. LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation
    • 8. CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
    • 9. NAISR: A 3D Neural Additive Model for Interpretable Shape Representation
    • 10. 3D Implicit Transporter for Temporally Consistent Keypoint Discovery
    • 11. Template-free Articulated Neural Point Clouds for Reposable View Synthesis
    • 12. Ditto: Building Digital Twins of Articulated Objects from Interaction
    • 13. CLA-NeRF: Category-Level Articulated Neural Radiance Field
    • 14. Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects
    • 15. Self-supervised Neural Articulated Shape and Appearance Models
    • 16. NARF22: Neural Articulated Radiance Fields for Configuration-Aware Rendering
    • 17. Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects
    • 18. A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation
    • 19. StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
  • Kinematic Inference
  • • 1. A3VLM: Actionable Articulation-Aware Vision Language Model
    • 2. Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects
    • 3. Learning to Infer Kinematic Hierarchies for Novel Object Instances
    • 4. Towards Understanding Articulated Objects
  • Manipulation
  • • 1. ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion
    • 2. Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking
    • 3. KinScene: Model-Based Mobile Manipulation of Articulated Scenes
    • 4. Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction
    • 5. UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models
    • 6. Sim2Real2: Actively Building Explicit Physics Model for Precise Articulated Object Manipulation
    • 7. DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects
    • 8. GAMMA: Generalizable Articulation Modeling and Manipulation for Articulated Objects
    • 9. Part-Guided 3D RL for Sim2Real Articulated Object Manipulation
    • 10. Learning Part Motion of Articulated Objects Using Spatially Continuous Neural Implicit Representations
    • 11. GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts
    • 12. FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects
    • 13. Neural Field Representations of Articulated Objects for Robotic Manipulation Planning
    • 14. Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
  • Motion Transfer
  • • 1. CA2T-Net: Category-Agnostic 3D Articulation Transfer from Single Image
    • 2. Command-driven Articulated Object Understanding and Manipulation
    • 3. Learning to Predict Part Mobility from a Single Static Snapshot
  • Reconstruction
  • • 1. CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects
    • 2. Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image
    • 3. Interaction-Driven Active 3D Reconstruction with Object Interiors
    • 4. Structure from Action: Learning Interactions for 3D Articulated Object Structure Discovery
  • Scene-level Reconstruction
  • • 1. Ditto in the house: Building articulation models of indoor scenes through interactive perception
  • Tracking
  • • 1. Category-Independent Articulated Object Tracking with Factor Graphs
    • 2. CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds
  • Credits