mlsanityData to 14 Oct 2026

Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training

arXiv 2305.02756 ↗First posted 4 May 2023cs.CV cs.GRcited by 25

Not on the map. Why?

Abstract (arXiv)

NeRF acquisition typically requires careful choice of near planes for the different cameras or suffers from background collapse, creating floating artifacts on the edges of the captured scene. The key insight of this work is that background collapse is caused by a higher density of samples in regions near cameras. As a result of this sampling imbalance, near-camera volumes receive significantly more gradients, leading to incorrect density buildup. We propose a gradient scaling approach to counter-balance this sampling imbalance, removing the need for near planes, while preventing background collapse. Our method can be implemented in a few lines, does not induce any significant overhead, and is compatible with most NeRF implementations.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 4 May 2023.

Builds on

24 of 32 references.

References · 24

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  7. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  11. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  12. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
12 more
  1. 2021Advances in Neural Renderingcited by 365
  2. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  3. 2019Neural Point-Based Graphicscited by 327
  4. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  5. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  6. 2020Free View Synthesiscited by 231
  7. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  8. 2020Stable View Synthesiscited by 165
  9. 2023Neural Point Catacaustics for Novel-View Synthesis of Reflectionscited by 82
  10. 2022Improved Direct Voxel Grid Optimization for Radiance Fields Reconstructioncited by 61
  11. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  12. 2022NPBG++: Accelerating Neural Point-Based Graphicscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 11; 2025: 8; 2026: 2.

25 papers.

Sort:

By area:

  1. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
  2. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  3. 2024A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesiscited by 37
  4. 2024VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Pointscited by 29
  5. 2023Fast View Synthesis of Casual Videos with Soup-of-Planescited by 22
  6. 2024Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splattingcited by 20
  7. 2023PyNeRF: Pyramidal Neural Radiance Fieldscited by 16
  8. 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Modelscited by 12
  9. 2024TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Trackscited by 12
  10. 2025AquaNeRF: Neural Radiance Fields in Underwater Media with Distractor Removalcited by 8
  11. 2025Stochastic Preconditioning for Neural Field Optimizationcited by 8
  12. 2023LAENeRF: Local Appearance Editing for Neural Radiance Fieldscited by 5
13 more
  1. 2024G3DR: Generative 3D Reconstruction in ImageNetcited by 5
  2. 2024Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse Viewcited by 4
  3. 2025Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representationcited by 4
  4. 2024Fast Sparse View Guided NeRF Update for Object Reconfigurationscited by 3
  5. 2025UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fieldscited by 3
  6. 2024Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutionscited by 1
  7. 2025FourieRF: Few-Shot NeRFs via Progressive Fourier Frequency Controlcited by 1
  8. 2026Physically Inspired Gaussian Splatting for HDR Novel View Synthesiscited by 1
  9. 2023RANRAC: Robust Neural Scene Representations via Random Ray Consensuscited by 0
  10. 2024Surface-Based Visibility-Guided Uncertainty for Continuous Active 3D Neural Reconstructioncited by 0
  11. 2025GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fieldscited by 0
  12. 2025NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Editscited by 0
  13. 2026Two-View Accumulation as the Primary Training Lever for Hybrid-Capture Gaussian Splatting: A Variance-Decomposition View of When Gradient Surgery Helpscited by 0