AI Paper Atlas

Research map / 3D vision / Depth and stereo

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

Xiaoxue Chen, Bhargav Chandaka, Chih-Hao Lin, Ya-Qin Zhang, David Forsyth, Hao Zhao, Shenlong Wang

ICCV 2025 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LiDAR-to-RGB albedo consistency loss (ablation)InvRGB+L relighting · RelightingPSNR: 29.97 -> 30.42Improved
add LiDAR-to-RGB albedo consistency loss (ablation)InvRGB+L relighting · RelightingLPIPS: 0.34 -> 0.30Improved
add LiDAR-to-RGB albedo consistency loss (ablation)InvRGB+L relighting · RelightingSSIM: 0.73 -> 0.72No clear effect
add LiDAR input (initialization and albedo consistency) to RGB-only inverse rendering (ablation)InvRGB+L · Waymo dynamic scene PBR reconstructionPSNR: 33.35 -> 34.76Improved
add dynamic scene graph nodes (ablation)InvRGB+L · Waymo dynamic scene PBR reconstructionPSNR: 29.13 -> 34.76Improved
add dynamic scene graph nodes (ablation)InvRGB+L · Waymo dynamic scene PBR reconstructionLPIPS: 0.21 -> 0.11Improved
add specular term to LiDAR reflectance (PBR instead of Lambertian) (ablation)InvRGB+L · LiDAR intensity ablation (one scene)Intensity RMSE: 0.0493 -> 0.0470Improved
add RGB-X diffusion albedo prior (ablation)InvRGB+L · Albedo estimation (qualitative)albedo smoothness, shadow ambiguityImproved
compare against LiDAR simulation baselines on intensityInvRGB+L · Waymo LiDAR intensity NVSIntensity RMSE avg: 0.073 -> 0.063Improved
fine-tune YOLOv5 with simulated nighttime images from daytime logsYOLOv5 · Waymo night detectionmAP@50: 0.236 -> 0.321Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy