mlsanityData to 7 Oct 2026

InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning

arXiv 2303.04508 ↗First posted 8 Mar 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous methods that have employed feature encoding to improve optimization speed, we further improve the reconstruction quality with minimal impact on optimization time by refining depth information. InFusionSurf addresses camera motion-induced blurs in each depth frame through a per-frame intrinsic refinement scheme. It incorporates the truncated signed distance field (TSDF) Fusion, a classical real-time 3D surface reconstruction method, as a pretraining tool for the feature grid, enhancing reconstruction details and training speed. Comparative quantitative and qualitative analyses show that InFusionSurf reconstructs scenes with high accuracy while maintaining optimization efficiency. The effectiveness of our intrinsic refinement and TSDF Fusion-based pretraining is further validated through an ablation study.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

32 of 44 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  9. 2021Multi-Stage Progressive Image Restorationcited by 813
  10. 2020Convolutional Occupancy Networkscited by 760
  11. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  12. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
20 more
  1. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  2. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  3. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  4. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  5. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  6. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  7. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  8. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  9. 2021Neural RGB-D Surface Reconstructioncited by 312
  10. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  11. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  12. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  13. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  14. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  15. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 107
  16. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 92
  17. 2022BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fieldscited by 80
  18. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70
  19. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  20. 2014Recent Progress in Image Deblurringcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Query Quantized Neural SLAMcited by 3