mlsanityData to 14 Oct 2026

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields

arXiv 2404.02155 ↗First posted 2 Apr 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Scale-ambiguity in 3D scene dimensions leads to magnitude-ambiguity of volumetric densities in neural radiance fields, i.e., the densities double when scene size is halved, and vice versa. We call this property alpha invariance. For NeRFs to better maintain alpha invariance, we recommend 1) parameterizing both distance and volume densities in log space, and 2) a discretization-agnostic initialization strategy to guarantee high ray transmittance. We revisit a few popular radiance field models and find that these systems use various heuristics to deal with issues arising from scene scaling. We test their behaviors and show our recipe to be more robust.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 38 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

25 of 38 references.

References · 25

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  10. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  11. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  12. 2021Volume Rendering of Neural Implicit Surfacescited by 996
13 more
  1. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  2. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  3. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  6. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  7. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  8. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  9. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  10. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  11. 2020Normalization Techniques in Training DNNs: Methodology, Analysis and Applicationcited by 90
  12. 2022Approximate Differentiable Rendering with Algebraic Surfacescited by 44
  13. 2023Flexible Techniques for Differentiable Rendering with 3D Gaussianscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Rebenchmarking Unsupervised Monocular 3D Occupancy Predictioncited by 0