mlsanityData to 14 Oct 2026

LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes

arXiv 2601.15283 ↗First posted 21 Jan 2026cs.CV cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

We present a novel approach for interactive light editing in indoor scenes from a single multi-view scene capture. Our method leverages a generative image-based light decomposition model that factorizes complex indoor scene illumination into its constituent light sources. This factorization enables independent manipulation of individual light sources, specifically allowing control over their state (on/off), chromaticity, and intensity. We further introduce multi-view lighting harmonization to ensure consistent propagation of the lighting decomposition across all scene views. This is integrated into a relightable 3D Gaussian splatting representation, providing real-time interactive control over the individual light sources. Our results demonstrate highly photorealistic lighting decomposition and relighting outcomes across diverse indoor scenes. We evaluate our method on both synthetic and real-world datasets and provide a quantitative and qualitative comparison to state-of-the-art techniques. For video results and interactive demos, see https://luxremix.github.io.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 86 of its 105 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

86 of 105 references.

References · 86

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  6. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  8. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  9. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  10. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  11. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  12. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
38 more
  1. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
  2. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  3. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 203
  4. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 182
  5. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  6. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 161
  7. 2024In-Context LoRA for Diffusion Transformerscited by 158
  8. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  9. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
  10. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 133
  11. 2023Relightable Gaussian Codec Avatarscited by 127
  12. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  13. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 96
  14. 2024DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generationcited by 93
  15. 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
  16. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  17. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 87
  18. 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
  19. 2023Intrinsic Image Diffusion for Indoor Single-view Material Estimationcited by 73
  20. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 67
  21. 2022Physically-Based Editing of Indoor Scene Lighting from a Single Imagecited by 62
  22. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  23. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 57
  24. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 57
  25. 2024IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracingcited by 54
  26. 2023Intrinsic Image Decomposition via Ordinal Shadingcited by 53
  27. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  28. 2021Self-supervised Outdoor Scene Relightingcited by 48
  29. 2021Neural Video Portrait Relighting in Real-time via Consistency Modelingcited by 46
  30. 2024GS^3: Efficient Relighting with Triple Gaussian Splattingcited by 44
  31. 2023I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFscited by 42
  32. 2024GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Renderingcited by 42
  33. 2025UniRelight: Learning Joint Decomposition and Synthesis for Video Relightingcited by 40
  34. 2025Light-A-Video: Training-free Video Relighting via Progressive Light Fusioncited by 39
  35. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 38
  36. 2025LightLab: Controlling Light Sources in Images with Diffusion Modelscited by 38
  37. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  38. 2024A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesiscited by 37

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 9.

9 papers.

  1. 2026GR3EN: Generative Relighting for 3D Environmentscited by 5
  2. 2026Do Image Editing Models Understand Lighting?cited by 1
  3. 2026Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relightingcited by 1
  4. 2026SyncLight: Single-Edit Multi-View Relightingcited by 0
  5. 2026LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relightingcited by 0
  6. 2026LumiTokens: 3D Relighting via Token-Space Lighting Transformationcited by 0
  7. 2026LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splattingcited by 0
  8. 2026LoRA Direction Extraction for Controllable Light Toggling in FLUX.1 Kontextcited by 0
  9. 2026LAMP: 3D Source-Aware Lighting Estimation at Multiple Pointscited by 0