mlsanityData to 7 Oct 2026

InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling

arXiv 2507.17613 ↗First posted 23 Jul 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics methods rely primarily on RGB observations and use LiDAR mainly for geometric information, often resulting in suboptimal material estimates due to visible light interference. We find that LiDAR's intensity values-captured with active illumination in a different spectral range-offer complementary cues for robust material estimation under variable lighting. Inspired by this, InvRGB+L leverages LiDAR intensity cues to overcome challenges inherent in RGB-centric inverse graphics through two key innovations: (1) a novel physics-based LiDAR shading model and (2) RGB-LiDAR material consistency losses. The model produces novel-view RGB and LiDAR renderings of urban and indoor scenes and supports relighting, night simulations, and dynamic object insertions, achieving results that surpass current state-of-the-art methods in both scene-level urban inverse rendering and LiDAR simulation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 23 Jul 2025.

Builds on

43 of 58 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2023Segment Anythingcited by 8,158
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  5. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  6. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  7. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
  8. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  9. 2023TensoIR: Tensorial Inverse Renderingcited by 166
  10. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 159
  11. 2024OmniRe: Omni Urban Scene Reconstructioncited by 159
  12. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
31 more
  1. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 138
  2. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  3. 2023Neural Kernel Surface Reconstructioncited by 102
  4. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  5. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  6. 2023Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenescited by 89
  7. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 86
  8. 2022Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracingcited by 78
  9. 2023Intrinsic Image Diffusion for Indoor Single-view Material Estimationcited by 73
  10. 2023Neural LiDAR Fields for Novel View Synthesiscited by 65
  11. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 63
  12. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  13. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  14. 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Modelscited by 55
  15. 2020EMLight: Lighting Estimation via Spherical Distribution Approximationcited by 47
  16. 2023LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fieldscited by 46
  17. 2023I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFscited by 42
  18. 2023General, Single-shot, Target-less, and Automatic LiDAR-Camera Extrinsic Calibration Toolboxcited by 41
  19. 2018LIME: Live Intrinsic Material Estimationcited by 33
  20. 2023Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimationcited by 22
  21. 2023UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Videocited by 22
  22. 2023Dynamic LiDAR Re-simulation using Compositional Neural Fieldscited by 22
  23. 2022PCGen: Point Cloud Generator for LiDAR Simulationcited by 20
  24. 2023LightSim: Neural Lighting Simulation for Urban Scenescited by 20
  25. 2024AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesiscited by 17
  26. 2023NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fieldscited by 16
  27. 2024LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splattingcited by 15
  28. 2024Reflectivity Is All You Need!: Advancing LiDAR Semantic Segmentationcited by 9
  29. 2024RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Imagecited by 7
  30. 2024Off-Road LiDAR Intensity Based Semantic Segmentationcited by 4
  31. 2023DPF: Learning Dense Prediction Fields with Weak Supervisioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstructioncited by 0
  2. 2026Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstructioncited by 0
  3. 2026SRUG: Shadow-Guided Relightable Urban Scene with Generation Modelcited by 0
  4. 2026BRDFusion: Physics Meets Generation for Urban Scene Inverse Renderingcited by 0