mlsanityData to 14 Oct 2026

Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field

arXiv 2406.07329 ↗First posted 11 Jun 2024cs.CV eess.IVcited by 12

Not on the map. Why?

Abstract (arXiv)

Radiance field methods represent the state of the art in reconstructing complex scenes from multi-view photos. However, these reconstructions often suffer from one or both of the following limitations: First, they typically represent scenes in low dynamic range (LDR), which restricts their use to evenly lit environments and hinders immersive viewing experiences. Secondly, their reliance on a pinhole camera model, assuming all scene elements are in focus in the input images, presents practical challenges and complicates refocusing during novel-view synthesis. Addressing these limitations, we present a lightweight method based on 3D Gaussian Splatting that utilizes multi-view LDR images of a scene with varying exposure times, apertures, and focus distances as input to reconstruct a high-dynamic-range (HDR) radiance field. By incorporating analytical convolutions of Gaussians based on a thin-lens camera model as well as a tonemapping module, our reconstructions enable the rendering of HDR content with flexible refocusing capabilities. We demonstrate that our combined treatment of HDR and depth of field facilitates real-time cinematic rendering, outperforming the state of the art.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 37 of its 78 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

37 of 78 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  9. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  10. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
  11. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  12. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
25 more
  1. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  2. 2023Multi-Scale 3D Gaussian Splatting for Anti-Aliased Renderingcited by 138
  3. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 132
  4. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 117
  5. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 114
  6. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  7. 2020HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motionscited by 80
  8. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  9. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70
  10. 2022Ghost-free High Dynamic Range Imaging with Context-aware Transformercited by 65
  11. 2023HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular contentcited by 41
  12. 2022HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fieldscited by 40
  13. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
  14. 2023Towards High-quality HDR Deghosting with Conditional Diffusion Modelscited by 33
  15. 2023Alignment-free HDR Deghosting with Semantics Consistent Transformercited by 32
  16. 2019Synthetic Defocus and Look-Ahead Autofocus for Casual Videographycited by 28
  17. 2022DoF-NeRF: Depth-of-Field Meets Neural Radiance Fieldscited by 26
  18. 2022GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wildcited by 21
  19. 2023Fully Self-Supervised Depth Estimation from Defocus Cluecited by 17
  20. 2017Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudescited by 15
  21. 2023SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoderscited by 11
  22. 2023Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenescited by 9
  23. 2022Learning Depth from Focus in the Wildcited by 8
  24. 2021Learning a self-supervised tone mapping operator via feature contrast masking losscited by 6
  25. 2022Gaussian Mixture Convolution Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 3.

12 papers.

  1. 2025Deformable Beta Splattingcited by 38
  2. 2025LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesiscited by 14
  3. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 12
  4. 2025GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mappingcited by 9
  5. 2025DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splattingcited by 6
  6. 2025Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videoscited by 2
  7. 2026NanoGS: Training-Free Gaussian Splat Simplificationcited by 2
  8. 2025Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videoscited by 1
  9. 2025Depth-Consistent 3D Gaussian Splatting via Physical Defocus Modeling and Multi-View Geometric Supervisioncited by 1
  10. 2025SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancementcited by 1
  11. 2026Physically Inspired Gaussian Splatting for HDR Novel View Synthesiscited by 1
  12. 2026Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstructioncited by 1