mlsanityData to 7 Oct 2026

PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction

arXiv 2601.18336 ↗First posted 26 Jan 2026cs.CV cs.GRcited by 7

Not on the map. Why?

Abstract (arXiv)

Multi-view 3D reconstruction methods remain highly sensitive to photometric inconsistencies arising from camera optical characteristics and variations in image signal processing (ISP). Existing mitigation strategies such as per-frame latent variables or affine color corrections lack physical grounding and generalize poorly to novel views. We propose the Physically-Plausible ISP (PPISP) correction module, which disentangles camera-intrinsic and capture-dependent effects through physically based and interpretable transformations. A dedicated PPISP controller, trained on the input views, predicts ISP parameters for novel viewpoints, analogous to auto exposure and auto white balance in real cameras. This design enables realistic and fair evaluation on novel views without access to ground-truth images. PPISP achieves state-of-the-art performance on standard benchmarks, while providing intuitive control and supporting the integration of metadata when available. The source code is available at: https://github.com/nv-tlabs/ppisp

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

26 of 38 references.

References · 26

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  6. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  7. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  8. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 279
  9. 2021Urban Radiance Fieldscited by 263
  10. 2024Global Structure-from-Motion Revisitedcited by 215
  11. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
  12. 2016Deep Image Homography Estimationcited by 135
14 more
  1. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  2. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  3. 2015Optimal whitening and decorrelationcited by 93
  4. 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 87
  5. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  6. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  7. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
  8. 2024Bilateral Guided Radiance Field Processingcited by 28
  9. 2021Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matchingcited by 13
  10. 2024Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variationcited by 13
  11. 2023Neural Lens Modelingcited by 7
  12. 2024SimVS: Simulating World Inconsistencies for Robust View Synthesiscited by 5
  13. 2025CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Predictioncited by 4
  14. 2025Learning Neural Exposure Fields for View Synthesiscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.