mlsanityData to 13 Oct 2026

Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction

arXiv 2108.08478 ↗First posted 19 Aug 2021cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details. In this paper, we propose a novel learnable Anchored Unsigned Distance Function (AnchorUDF) representation for 3D garment reconstruction from a single image. AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution. To capture diverse garment topologies, AnchorUDF not only computes pixel-aligned local image features of query points, but also leverages a set of anchor points located around the surface to enrich 3D position features for query points, which provides stronger 3D space context for the distance function. Furthermore, in order to obtain more accurate point projection direction at inference, we explicitly align the spatial gradient direction of AnchorUDF with the ground-truth direction to the surface during training. Extensive experiments on two public 3D garment datasets, i.e., MGN and Deep Fashion3D, demonstrate that AnchorUDF achieves the state-of-the-art performance on single-view garment reconstruction.

Key facts. Cited by 36 papers in the map (data through 13 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

33 of 43 references.

References · 33

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,039
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,603
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 976
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 708
  8. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 650
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
21 more
  1. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  2. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  3. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  4. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  5. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  6. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  7. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  8. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  9. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  10. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  11. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  12. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  13. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  14. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 118
  15. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  16. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  17. 2018Detailed Human Avatars from Monocular Videocited by 109
  18. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 101
  19. 2018DeepWrinkles: Accurate and Realistic Clothing Modelingcited by 90
  20. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  21. 2019SimulCap : Single-View Human Performance Capture with Cloth Simulationcited by 41

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 16; 2024: 7; 2025: 3; 2026: 2.

36 papers.

Sort:

By area:

  1. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  2. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 75
  3. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  4. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  5. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  6. 2022DrapeNet: Garment Generation and Self-Supervised Drapingcited by 39
  7. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  8. 2023Towards Garment Sewing Pattern Reconstruction from a Single Imagecited by 33
  9. 2023REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videoscited by 29
  10. 20223PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologiescited by 27
  11. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 21
  12. 2025Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physicscited by 19
24 more
  1. 2022Structure-Preserving 3D Garment Modeling with Neural Sewing Machinescited by 18
  2. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  3. 2024Generative AI Models for Different Steps in Architectural Design: A Literature Reviewcited by 12
  4. 2024Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentationcited by 11
  5. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  6. 2024Neural-ABC: Neural Parametric Models for Articulated Body with Clothescited by 9
  7. 20232S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Imagescited by 7
  8. 2023Learning Anchor Transformations for 3D Garment Animationcited by 7
  9. 2023LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstructioncited by 6
  10. 2023SuperUDF: Self-supervised UDF Estimation for Surface Reconstructioncited by 6
  11. 2023Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fieldscited by 5
  12. 2023High-Quality Animatable Dynamic Garment Reconstruction from Monocular Videoscited by 5
  13. 2024Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversariescited by 5
  14. 2023A Generative Multi-Resolution Pyramid and Normal-Conditioning 3D Cloth Drapingcited by 4
  15. 2023Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularizationcited by 2
  16. 2023DeepIron: Predicting Unwarped Garment Texture from a Single Imagecited by 2
  17. 2024A Latent Implicit 3D Shape Model for Multiple Levels of Detailcited by 2
  18. 2025High Resolution UDF Meshing via Iterative Networkscited by 2
  19. 2022Automated Reconstruction of 3D Open Surfaces from Sparse Point Cloudscited by 1
  20. 2023IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstructioncited by 0
  21. 2024Gradient Distance Functioncited by 0
  22. 2025Neural Shortest Path for Surface Reconstruction from Point Cloudscited by 0
  23. 2026PhysDrape: Learning Explicit Forces and Collision Constraints for Physically Realistic Garment Drapingcited by 0
  24. 2026SewFusion: Tailored Generation of Topology and Panel-Level Geometry for Sewing Patternscited by 0