mlsanityData to 7 Oct 2026

GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction

arXiv 2206.14735 ↗First posted 29 Jun 2022cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

We present GO-Surf, a direct feature grid optimization method for accurate and fast surface reconstruction from RGB-D sequences. We model the underlying scene with a learned hierarchical feature voxel grid that encapsulates multi-level geometric and appearance local information. Feature vectors are directly optimized such that after being tri-linearly interpolated, decoded by two shallow MLPs into signed distance and radiance values, and rendered via surface volume rendering, the discrepancy between synthesized and observed RGB/depth values is minimized. Our supervision signals -- RGB, depth and approximate SDF -- can be obtained directly from input images without any need for fusion or post-processing. We formulate a novel SDF gradient regularization term that encourages surface smoothness and hole filling while maintaining high frequency details. GO-Surf can optimize sequences of 1-2K frames in 15-45 minutes, a speedup of ×60 over NeuralRGB-D, the most related approach based on an MLP representation, while maintaining on par performance on standard benchmarks. Project page: https://jingwenwang95.github.io/gosurf/

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 29 Jun 2022.

Builds on

33 of 41 references.

References · 33

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  9. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  10. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
21 more
  1. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  2. 2020Convolutional Occupancy Networkscited by 760
  3. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  5. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  6. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  7. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  8. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  9. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  10. 2021Neural RGB-D Surface Reconstructioncited by 312
  11. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  12. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  13. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  14. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  15. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  16. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  17. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 107
  18. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
  19. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  20. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  21. 2021VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusioncited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 18; 2024: 23; 2025: 10; 2026: 3.

61 papers.

Sort:

By area:

  1. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
  2. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  3. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  4. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  5. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  6. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 92
  7. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  8. 2023ENVIDR: Implicit Differentiable Renderer with Neural Environment Lightingcited by 63
  9. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  10. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  11. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  12. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
38 more
  1. 2022SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representationscited by 44
  2. 2024PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistencycited by 42
  3. 2023Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensorcited by 30
  4. 2024SPA: 3D Spatial-Awareness Enables Effective Embodied Representationcited by 28
  5. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 27
  6. 2022PIXEL: Physics-Informed Cell Representations for Fast and Accurate PDE Solverscited by 22
  7. 2023Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracingcited by 22
  8. 2023NViST: In the Wild New View Synthesis from a Single Image with Transformerscited by 19
  9. 2024MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstructioncited by 18
  10. 2024VRP-UDF: Towards Unbiased Learning of Unsigned Distance Functions from Multi-view Images with Volume Rendering Priorscited by 17
  11. 2023MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesiscited by 12
  12. 2025NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstructioncited by 12
  13. 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priorscited by 11
  14. 2025MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representationcited by 11
  15. 2024AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphonescited by 10
  16. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9
  17. 2023O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Modelcited by 8
  18. 2025VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussianscited by 8
  19. 2024Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-mapscited by 7
  20. 2024OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representationcited by 6
  21. 2024NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensationcited by 5
  22. 20233D Reconstruction with Generalizable Neural Fields using Scene Priorscited by 4
  23. 2023DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction with an Optimizable Feature Gridcited by 4
  24. 2024CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesiscited by 4
  25. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  26. 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussianscited by 4
  27. 2023Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstructioncited by 3
  28. 2023Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancementcited by 3
  29. 2024Improving Neural Surface Reconstruction with Feature Priors from Multi-View Imagecited by 3
  30. 2023MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Videocited by 2
  31. 2024Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completioncited by 2
  32. 2024Distributed NeRF Learning for Collaborative Multi-Robot Perceptioncited by 2
  33. 2025RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstructioncited by 2
  34. 2023InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learningcited by 1
  35. 20243D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Fieldcited by 1
  36. 2024Stable Surface Regularization for Fast Few-Shot NeRFcited by 1
  37. 2024nu-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstructioncited by 1
  38. 2024Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor Environmentcited by 1

50 most cited of 61 All 61 (JSON)