mlsanityData to 14 Oct 2026

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views

arXiv 2206.05737 ↗First posted 12 Jun 2022cs.CVcited by 177

Not on the map. Why?

Cited by 34 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. This task becomes more difficult when only sparse images are provided as input, a scenario where existing neural reconstruction approaches usually produce incomplete or distorted results. Moreover, their inability of generalizing to unseen new scenes impedes their application in practice. Contrarily, SparseNeuS can generalize to new scenes and work well with sparse images (as few as 2 or 3). SparseNeuS adopts signed distance function (SDF) as the surface representation, and learns generalizable priors from image features by introducing geometry encoding volumes for generic surface prediction. Moreover, several strategies are introduced to effectively leverage sparse views for high-quality reconstruction, including 1) a multi-level geometry reasoning framework to recover the surfaces in a coarse-to-fine manner; 2) a multi-scale color blending scheme for more reliable color prediction; 3) a consistency-aware fine-tuning scheme to control the inconsistent regions caused by occlusion and noise. Extensive experiments demonstrate that our approach not only outperforms the state-of-the-art methods, but also exhibits good efficiency, generalizability, and flexibility.

Key facts. Cited by 177 papers in the map (data through 14 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

37 of 53 references.

References · 37

  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  8. 2020Neural Sparse Voxel Fieldscited by 959
  9. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
25 more
  1. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  2. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  3. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  4. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  5. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  6. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  7. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  8. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  9. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  10. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  11. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  12. 2017Learning a Multi-View Stereo Machinecited by 194
  13. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  14. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  15. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  16. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 180
  17. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  18. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  19. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  20. 2021Neural Lumigraph Renderingcited by 105
  21. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  22. 2020Multi-view Depth Estimation using Epipolar Spatio-Temporal Networkscited by 59
  23. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  24. 2020Occlusion-Aware Depth Estimation with Adaptive Normal Constraintscited by 41
  25. 2020SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsiscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 45; 2024: 73; 2025: 38; 2026: 12.

177 papers.

Sort:

By area:

  1. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  2. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  3. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  5. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  6. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  7. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  8. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  9. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  10. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  11. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  12. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
38 more
  1. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  2. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
  3. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  4. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  5. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  6. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  7. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  8. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  9. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
  10. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  11. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  12. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  13. 20243D Gaussian as a New Era: A Surveycited by 104
  14. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  15. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 89
  16. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusioncited by 72
  17. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 68
  18. 2022Removing Objects From Neural Radiance Fieldscited by 66
  19. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  20. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 62
  21. 2024Representing Long Volumetric Video with Temporal Gaussian Hierarchycited by 58
  22. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  23. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 55
  24. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  25. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 53
  26. 2024GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplanecited by 53
  27. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  28. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 41
  29. 2023VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encodercited by 39
  30. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 37
  31. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  32. 2024G3R: Gradient Guided Generalizable Reconstructioncited by 31
  33. 2025FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistencycited by 31
  34. 2023ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstructioncited by 30
  35. 2023GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generationcited by 30
  36. 2023UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflectionscited by 30
  37. 2023ResFields: Residual Neural Fields for Spatiotemporal Signalscited by 27
  38. 2024Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Modelscited by 27

50 most cited of 177 All 177 (JSON)