mlsanityData to 14 Oct 2026

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

arXiv 1905.10711 ↗First posted 26 May 2019cs.CVcited by 333

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Reconstructing 3D shapes from single-view images has been a long-standing research problem. In this paper, we present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting the underlying signed distance fields. In addition to utilizing global image features, DISN predicts the projected location for each 3D point on the 2D image, and extracts local features from the image feature maps. Combining global and local features significantly improves the accuracy of the signed distance field prediction, especially for the detail-rich areas. To the best of our knowledge, DISN is the first method that constantly captures details such as holes and thin structures present in 3D shapes from single-view images. DISN achieves the state-of-the-art single-view reconstruction performance on a variety of shape categories reconstructed from both synthetic and real images. Code is available at https://github.com/xharlie/DISN The supplementary can be found at https://xharlie.github.io/images/neurips_2019_supp.pdf

Key facts. Cited by 333 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 82; 2022: 92; 2023: 77; 2024: 48; 2025: 25; 2026: 9.

333 papers.

Sort:

By area:

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  2. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  3. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  4. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  5. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  7. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  8. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  9. 2021Neural Fields in Visual Computing and Beyondcited by 540
  10. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  11. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  12. 2021Advances in Neural Renderingcited by 365
38 more
  1. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  2. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  3. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  4. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  5. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  6. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  7. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  8. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  9. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  10. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  11. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  12. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  13. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  14. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 160
  15. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
  16. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  17. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 130
  18. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  19. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  20. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 118
  21. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  22. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  23. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 108
  24. 2021Light Field Neural Renderingcited by 108
  25. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  26. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  27. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  28. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  29. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  30. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  31. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  32. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  33. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  34. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  35. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  36. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  37. 2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
  38. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64

50 most cited of 333 All 333 (JSON)