mlsanityData to 14 Oct 2026

Vox-Surf: Voxel-based Implicit Surface Representation

arXiv 2208.10925 ↗First posted 21 Aug 2022cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. We propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite bounded voxels. Each voxel stores geometry and appearance information in its corner vertices. Vox-Surf is suitable for almost any scenario thanks to sparsity inherited from voxel representation and can be easily trained from multiple view images. We leverage the progressive training procedure to extract important voxels gradually for further optimization so that only valid voxels are preserved, which greatly reduces the number of sampling points and increases rendering speed.The fine voxels can also be considered as the bounding volume for collision detection.The experiments show that Vox-Surf representation can learn delicate surface details and accurate color with less memory and faster rendering speed than other methods.We also show that Vox-Surf can be more practical in scene editing and AR applications.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 21 Aug 2022.

Builds on

30 of 44 references.

References · 30

  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  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. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 710
18 more
  1. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  2. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  4. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  5. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  6. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  7. 2016Direct Sparse Odometrycited by 485
  8. 2017Neural 3D Mesh Renderercited by 437
  9. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  10. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  11. 2021Neural RGB-D Surface Reconstructioncited by 313
  12. 2021Urban Radiance Fieldscited by 263
  13. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 260
  14. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  15. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 142
  16. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  17. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  18. 2022Neural 3D Reconstruction in the Wildcited by 79

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 16; 2024: 15; 2025: 14; 2026: 3.

49 papers.

Sort:

By area:

  1. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  2. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  3. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 184
  4. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  5. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  6. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  7. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  8. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 94
  9. 2024SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Realitycited by 43
  10. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 33
  11. 2023CP-SLAM: Collaborative Neural Point-based SLAM Systemcited by 32
  12. 2023MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstructioncited by 24
37 more
  1. 2023Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracingcited by 22
  2. 2024NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understandingcited by 19
  3. 2023ECNR: Efficient Compressive Neural Representation of Time-Varying Volumetric Datasetscited by 17
  4. 2025PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understandingcited by 16
  5. 2025TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priorscited by 14
  6. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  7. 2024ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstructioncited by 11
  8. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  9. 2023RD-VIO: Robust Visual-Inertial Odometry for Mobile Augmented Reality in Dynamic Environmentscited by 9
  10. 2024O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representationcited by 9
  11. 2023FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Modelscited by 7
  12. 2024Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-mapscited by 7
  13. 2024OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctreescited by 6
  14. 2024Sur2f: A Hybrid Representation for High-Quality and Efficient Surface Reconstruction from Multi-view Imagescited by 5
  15. 2025NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Featurescited by 5
  16. 2023InstantAvatar: Efficient 3D Head Reconstruction via Surface Renderingcited by 4
  17. 2024PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstructioncited by 4
  18. 2025SP-SLAM: Neural Real-Time Dense SLAM With Scene Priorscited by 4
  19. 2025Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstructioncited by 4
  20. 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussianscited by 4
  21. 2023PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstructioncited by 3
  22. 2024GBR: Generative Bundle Refinement for High-fidelity Gaussian Splatting with Enhanced Mesh Reconstructioncited by 3
  23. 2025Thermoxels: a voxel-based method to generate simulation-ready 3D thermal modelscited by 3
  24. 2026OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splattingcited by 2
  25. 2025NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devicescited by 1
  26. 2025FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representationscited by 1
  27. 2025Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wildcited by 1
  28. 2025Camera Pose Refinement via 3D Gaussian Splattingcited by 1
  29. 2026Advancing Structured Priors for Sparse-Voxel Surface Reconstructioncited by 1
  30. 2024LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updatingcited by 0
  31. 2024DF-SLAM: Dictionary Factors Representation for High-Fidelity Neural Implicit Dense Visual SLAM Systemcited by 0
  32. 2024VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolationcited by 0
  33. 2024A Comparative Study of Neural Surface Reconstruction for Scientific Visualizationcited by 0
  34. 2025Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learningcited by 0
  35. 2025GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstructioncited by 0
  36. 2025CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representationcited by 0
  37. 2026Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimizationcited by 0