mlsanityData to 7 Oct 2026

GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion

arXiv 2104.05177 ↗First posted 12 Apr 2021cs.CV cs.LG cs.ROcited by 41

Not on the map. Why?

Abstract (arXiv)

This paper tackles the task of category-level pose estimation for garments. With a near infinite degree of freedom, a garment's full configuration (i.e., poses) is often described by the per-vertex 3D locations of its entire 3D surface. However, garments are also commonly subject to extreme cases of self-occlusion, especially when folded or crumpled, making it challenging to perceive their full 3D surface. To address these challenges, we propose GarmentNets, where the key idea is to formulate the deformable object pose estimation problem as a shape completion task in the canonical space. This canonical space is defined across garments instances within a category, therefore, specifies the shared category-level pose. By mapping the observed partial surface to the canonical space and completing it in this space, the output representation describes the garment's full configuration using a complete 3D mesh with the per-vertex canonical coordinate label. To properly handle the thin 3D structure presented on garments, we proposed a novel 3D shape representation using the generalized winding number field. Experiments demonstrate that GarmentNets is able to generalize to unseen garment instances and achieve significantly better performance compared to alternative approaches.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

24 of 37 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  8. 2018PCN: Point Completion Networkcited by 382
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  10. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  11. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  12. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
12 more
  1. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  2. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  3. 2019Category-Level Articulated Object Pose Estimationcited by 158
  4. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 148
  5. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  6. 2017Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matchingcited by 124
  7. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 118
  8. 2019CLOTH3D: Clothed 3D Humanscited by 114
  9. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  10. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 101
  11. 2016VolumeDeform: Real-time Volumetric Non-rigid Reconstructioncited by 75
  12. 2021Occlusion-robust Deformable Object Tracking without Physics Simulationcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 9; 2024: 10; 2025: 10; 2026: 5.

41 papers.

Sort:

By area:

  1. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 56
  2. 2021FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policycited by 54
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  4. 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
  5. 2022Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulationcited by 32
  6. 2023Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariancecited by 26
  7. 2023Learning Foresightful Dense Visual Affordance for Deformable Object Manipulationcited by 25
  8. 2023ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environmentcited by 22
  9. 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 22
  10. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  11. 2022Visuotactile Affordances for Cloth Manipulation with Local Controlcited by 20
  12. 2025Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulationcited by 16
29 more
  1. 2023GarmentTracking: Category-Level Garment Pose Trackingcited by 15
  2. 2022Layered-Garment Net: Generating Multiple Implicit Garment Layers from a Single Imagecited by 9
  3. 2023Self-supervised Cloth Reconstruction via Action-conditioned Cloth Trackingcited by 8
  4. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  5. 2024Reconstruction of Manipulated Garment with Guided Deformation Priorcited by 8
  6. 2023Learning Anchor Transformations for 3D Garment Animationcited by 7
  7. 2025Cloth-Splatting: 3D Cloth State Estimation from RGB Supervisioncited by 7
  8. 2022Garment Avatars: Realistic Cloth Driving using Pattern Registrationcited by 6
  9. 2022Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactionscited by 5
  10. 2024TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approachcited by 5
  11. 2025InstructionBench: An Instructional Video Understanding Benchmarkcited by 5
  12. 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Imagecited by 5
  13. 2024PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Roboticscited by 4
  14. 2025Reactive In-Air Clothing Manipulation with Confidence-Aware Dense Correspondence and Visuotactile Affordancecited by 4
  15. 2025R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulationcited by 4
  16. 2024Fast Sparse View Guided NeRF Update for Object Reconfigurationscited by 3
  17. 2025GraphGarment: Learning Garment Dynamics for Bimanual Cloth Manipulation Taskscited by 3
  18. 2025You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Graspingcited by 3
  19. 2023MARF: The Medial Atom Ray Field Object Representationcited by 2
  20. 2024Equivariant Local Reference Frames for Unsupervised Non-rigid Point Cloud Shape Correspondencecited by 2
  21. 2026DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spacescited by 2
  22. 2024RaggeDi: Diffusion-based State Estimation of Disordered Rags, Sheets, Towels and Blanketscited by 1
  23. 2024Implicit Contact Diffuser: Sequential Contact Reasoning with Latent Point Cloud Diffusioncited by 1
  24. 2025Learning a General Model: Folding Clothing with Topological Dynamicscited by 1
  25. 2026NGL: Natural Garment Language for Training-Free Sewing Pattern Estimationcited by 1
  26. 2025Beyond Static Perception: Integrating Temporal Context into VLMs for Cloth Foldingcited by 0
  27. 2026OCH3R: Object-Centric Holistic 3D Reconstructioncited by 0
  28. 2026Topology-Agnostic Mesh Reconstruction of Deformable Objects from Sparse Touchcited by 0
  29. 2026SewFusion: Tailored Generation of Topology and Panel-Level Geometry for Sewing Patternscited by 0