mlsanityData to 14 Oct 2026

Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence

arXiv 2503.21766 ↗First posted 27 Mar 2025cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Establishing character shape correspondence is a critical and fundamental task in computer vision and graphics, with diverse applications including re-topology, attribute transfer, and shape interpolation. Current dominant functional map methods, while effective in controlled scenarios, struggle in real situations with more complex challenges such as non-isometric shape discrepancies. In response, we revisit registration-for-correspondence methods and tap their potential for more stable shape correspondence estimation. To overcome their common issues including unstable deformations and the necessity for careful pre-alignment or high-quality initial 3D correspondences, we introduce Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence. We first re-purpose a foundation model for 2D character correspondence that ensures reliable and stable 2D mappings. Crucially, we propose a novel Semantic Flow Guided Registration approach that leverages 2D correspondence to guide mesh deformations. Our framework significantly surpasses existing methods in challenging scenarios, and brings possibilities for a wide array of real applications, as demonstrated in our results.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 62 of its 87 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

62 of 87 references.

References · 62

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  6. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  7. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  8. 2023Emergent Correspondence from Image Diffusioncited by 446
  9. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  10. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  11. 2017Learning from Synthetic Humanscited by 359
  12. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
38 more
  1. 2021Deep ViT Features as Dense Visual Descriptorscited by 330
  2. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  3. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  4. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  5. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 257
  6. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  7. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 214
  8. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 213
  9. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  10. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 164
  11. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 146
  12. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  13. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  14. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 124
  15. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  16. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  17. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  18. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  19. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  20. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 86
  21. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  22. 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
  23. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  24. 2020Deep Shells: Unsupervised Shape Correspondence with Optimal Transportcited by 74
  25. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  26. 2023DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphingcited by 67
  27. 2023Unsupervised Learning of Robust Spectral Shape Matchingcited by 57
  28. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  29. 2024VideoMV: Consistent Multi-View Generation Based on Large Video Generative Modelcited by 45
  30. 2022Non-rigid Point Cloud Registration with Neural Deformation Pyramidcited by 42
  31. 2022Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matchingcited by 35
  32. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  33. 2023Spatially and Spectrally Consistent Deep Functional Mapscited by 30
  34. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  35. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  36. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 27
  37. 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolationcited by 26
  38. 2020MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignmentcited by 20

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Hierarchical Neural Semantic Representation for 3D Semantic Correspondencecited by 14
  2. 2025Do It Yourself: Learning Semantic Correspondence from Pseudo-Labelscited by 13
  3. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  4. 2025SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussianscited by 1
  5. 2026SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signalscited by 1
  6. 2026RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfercited by 0
  7. 2026NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objectscited by 0