mlsanityData to 7 Oct 2026

MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation

arXiv 2504.09149 ↗First posted 12 Apr 2025cs.CV cs.CGcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the importance of perceptual shape understanding for learning 3D shapes, MASH represents a 3D shape as a collection of observable local surface patches, each defined by a spherical distance function emanating from an anchor point. We further leverage the compactness of spherical harmonics to encode the MASH functions, combined with a generalized view cone with a parameterized base that masks the spatial extent of the spherical function to attain locality. We develop a differentiable optimization algorithm capable of converting any point cloud into a MASH representation accurately approximating ground-truth surfaces with arbitrary geometry and topology. Extensive experiments demonstrate that MASH is versatile for multiple applications including surface reconstruction, shape generation, completion, and blending, achieving superior performance thanks to its unique representation encompassing both implicit and explicit features.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 64 references that are in the map. First posted on arXiv 12 Apr 2025.

Builds on

32 of 64 references.

References · 32

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2020Convolutional Occupancy Networkscited by 760
  11. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  12. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
20 more
  1. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  5. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  6. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  7. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  8. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  9. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  10. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  11. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  12. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  13. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generationcited by 82
  14. 2018MeshCNN: A Network with an Edgecited by 69
  15. 2023Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstructioncited by 49
  16. 2018A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshescited by 39
  17. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  18. 2024Make-A-Shape: a Ten-Million-scale 3D Shape Modelcited by 25
  19. 2020Learning Delaunay Surface Elements for Mesh Reconstructioncited by 23
  20. 2023NeRFs: The Search for the Best 3D Representationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Castingcited by 3
  2. 2025HPR3D: Hierarchical Proxy Representation for High-Fidelity 3D Reconstruction and Controllable Editingcited by 0
  3. 2026SHARC: Reference point driven Spherical Harmonic Representation for Complex Shapescited by 0
  4. 2026Blended Chart Surfaces: A Seamless Explicit Representation for Smooth Surface Fittingcited by 0