mlsanityData to 7 Oct 2026

Casual Indoor HDR Radiance Capture from Omnidirectional Images

arXiv 2208.07903 ↗First posted 16 Aug 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, which are used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF can render full HDR images from any location of the scene. Through experiments on a novel test dataset of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible HDR radiance from any scene point. We also show that the predicted radiance can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly. Datasets and code are available at https://lvsn.github.io/PanoHDR-NeRF/.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 16 Aug 2022.

Builds on

38 of 60 references.

References · 38

  1. 2017Mask R-CNNcited by 7,259
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  8. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  9. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  12. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
26 more
  1. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  2. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  3. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  4. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  5. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  6. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  7. 2020Free View Synthesiscited by 231
  8. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  9. 2020Stable View Synthesiscited by 165
  10. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  11. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  12. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
  13. 2019Neural Rerendering in the Wildcited by 121
  14. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  15. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  16. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  17. 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64
  18. 2019Instance Shadow Detectioncited by 37
  19. 2017Learning High Dynamic Range from Outdoor Panoramascited by 34
  20. 2018Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Imagecited by 25
  21. 2020Deep Multi Depth Panoramas for View Synthesiscited by 20
  22. 2021Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panoramacited by 19
  23. 2021Luminance Attentive Networks for HDR Image and Panorama Reconstructioncited by 18
  24. 2021Layout-Guided Novel View Synthesis from a Single Indoor Panoramacited by 16
  25. 2022Enhancement of Novel View Synthesis Using Omnidirectional Image Completioncited by 9
  26. 2022Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objectscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 3.

11 papers.

  1. 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
  2. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  3. 2022360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidancecited by 23
  4. 2023Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Predictioncited by 14
  5. 2024Fast High Dynamic Range Radiance Fields for Dynamic Scenescited by 13
  6. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 11
  7. 2023Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Imagescited by 7
  8. 2025ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularizationcited by 4
  9. 2025OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blendercited by 2
  10. 2022StyleTRF: Stylizing Tensorial Radiance Fieldscited by 1
  11. 2024PanDORA: Casual HDR Radiance Acquisition of Indoor Scenes for Image-based Lightingcited by 0