mlsanityData to 7 Oct 2026

Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

arXiv 2206.05085 ↗First posted 10 Jun 2022cs.GRcited by 61

Not on the map. Why?

Abstract (arXiv)

In this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 30; 2024: 16; 2025: 6; 2026: 2.

61 papers.

Sort:

By area:

  1. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  2. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  3. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  4. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  5. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 92
  6. 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
  7. 2023Segment Anything in 3D with Radiance Fieldscited by 61
  8. 2022Interactive Segmentation of Radiance Fieldscited by 60
  9. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  10. 2023Binary Radiance Fieldscited by 39
  11. 2022ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Fieldcited by 37
  12. 2023Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Featurescited by 36
38 more
  1. 2023DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelinescited by 35
  2. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 29
  3. 2024Trim 3D Gaussian Splatting for Accurate Geometry Representationcited by 28
  4. 2022Cross-Spectral Neural Radiance Fieldscited by 27
  5. 2023Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Trainingcited by 25
  6. 2024Thermal-NeRF: Neural Radiance Fields from an Infrared Cameracited by 21
  7. 2022PeRFception: Perception using Radiance Fieldscited by 19
  8. 2023MV-Map: Offboard HD-Map Generation with Multi-view Consistencycited by 19
  9. 2023SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenescited by 19
  10. 2024GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Qualitycited by 17
  11. 2023VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputscited by 16
  12. 2024Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Imagescited by 16
  13. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  14. 2023Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fieldscited by 14
  15. 2022CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representationscited by 13
  16. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  17. 2024D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Videocited by 11
  18. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  19. 2025Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representationcited by 11
  20. 2023NeRF Revisited: Fixing Quadrature Instability in Volume Renderingcited by 10
  21. 2023ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimizationcited by 8
  22. 2024Grounding and Enhancing Grid-based Models for Neural Fieldscited by 8
  23. 2024Efficient Depth-Guided Urban View Synthesiscited by 7
  24. 2024RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videoscited by 7
  25. 2025Anti-Aliased 2D Gaussian Splattingcited by 7
  26. 2024Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistencycited by 6
  27. 2024GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lightingcited by 6
  28. 2023Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representationscited by 5
  29. 2023MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Tablecited by 4
  30. 2023MMPI: a Flexible Radiance Field Representation by Multiple Multi-plane Images Blendingcited by 4
  31. 2023CAwa-NeRF: Instant Learning of Compression-Aware NeRF Featurescited by 4
  32. 2023Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstructioncited by 3
  33. 2023SLS4D: Sparse Latent Space for 4D Novel View Synthesiscited by 3
  34. 2024Unveiling the Ambiguity in Neural Inverse Rendering: A Parameter Compensation Analysiscited by 3
  35. 2025RGS-DR: Deferred Reflections and Residual Shading in 2D Gaussian Splattingcited by 3
  36. 2025TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splattingcited by 3
  37. 2023Evaluate Geometry of Radiance Fields with Low-frequency Color Priorcited by 2
  38. 2023Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Sizecited by 2

50 most cited of 61 All 61 (JSON)