mlsanityData to 7 Oct 2026

ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion

arXiv 2502.02187 ↗First posted 4 Feb 2025cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and point, normal, and color sampling within a multiscale neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can handle more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 100 of its 130 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

100 of 130 references.

References · 100

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2015Variational Inference with Normalizing Flowscited by 2,161
  10. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  11. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  12. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
38 more
  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  3. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  4. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  5. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2019An Introduction to Variational Autoencoderscited by 997
  8. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  9. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  10. 2016Pixel Recurrent Neural Networkscited by 814
  11. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  12. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  13. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  14. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  15. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  16. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  17. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  18. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  19. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  20. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  21. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  22. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  23. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  24. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  25. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  26. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  27. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  28. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  29. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  30. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  31. 2017Neural 3D Mesh Renderercited by 437
  32. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  33. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  34. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  35. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  36. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  37. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  38. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344

50 most cited of 100 All 100 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 20253D Shape Generation: A Surveycited by 0
  2. 2026EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Modelscited by 0
  3. 2026SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generationcited by 0