mlsanityData to 7 Oct 2026

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

arXiv 1901.05103 ↗First posted 16 Jan 2019cs.CVcited by 2,682

Not on the map. Why?

Cited by 144 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Computer graphics, 3D computer vision and robotics communities have produced multiple approaches to representing 3D geometry for rendering and reconstruction. These provide trade-offs across fidelity, efficiency and compression capabilities. In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data. DeepSDF, like its classical counterpart, represents a shape's surface by a continuous volumetric field: the magnitude of a point in the field represents the distance to the surface boundary and the sign indicates whether the region is inside (-) or outside (+) of the shape, hence our representation implicitly encodes a shape's boundary as the zero-level-set of the learned function while explicitly representing the classification of space as being part of the shapes interior or not. While classical SDF's both in analytical or discretized voxel form typically represent the surface of a single shape, DeepSDF can represent an entire class of shapes. Furthermore, we show state-of-the-art performance for learned 3D shape representation and completion while reducing the model size by an order of magnitude compared with previous work.

Key facts. Cited by 2,682 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 350; 2022: 514; 2023: 628; 2024: 540; 2025: 388; 2026: 262.

2,682 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  11. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  12. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
38 more
  1. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  2. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  3. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  4. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  5. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  6. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  7. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  8. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  9. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  10. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  11. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  12. 2021Neural Fields in Visual Computing and Beyondcited by 539
  13. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 537
  14. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  15. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  16. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  17. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  18. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  19. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  20. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  21. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  22. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  23. 2021Implicit Behavioral Cloningcited by 442
  24. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  25. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  26. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  27. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  28. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  29. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  30. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  31. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  32. 2021Advances in Neural Renderingcited by 365
  33. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  34. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  35. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  36. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  37. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  38. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324

50 most cited of 2,682 All 2,682 (JSON)