analiza aiqbench
This research advances 3D Gaussian Splatting by enabling relightable reconstruction under dynamic illumination, directly addressing critical challenges in robotic perception within low-light conditions. By jointly optimizing lighting parameters and incorporating non-Lambertian reflectance models, the method improves geometric consistency without relying on explicit light calibration or standard 2D enhancement techniques. The study demonstrates significant gains in rendering quality and downstream task performance using both synthetic data and real-world datasets involving uneven onboard lighting.
SpotlessGS: Relightable 3D Gaussian Splatting under Dynamic Illumination for Robotic Perception
arXiv:2608.14713v1 Announce Type: new Abstract: Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perception tasks. Prior approaches based on 2D image enhancement lack reliable supervision and fail to preserve multi-view geometric consistency. To address these limitations, we extend Dark Gaussian Splatting (DarkGS) toward a more accurate and flexible relightable 3D reconstruction framework. First, we eliminate the need for explicit light parameter calibration by jointly optimizing lighting parameters within the Gaussian Splatting framework. Second, we introduce a low-frequency illumination model based on spherical harmonics (SH) to capture spatially varying residual and ambient lighting effects. Third, we incorporate an MLP-based Bidirectional Reflectance Distribution Function (BRDF) to model non-Lambertian reflectance. Experiments on synthetic and real-world datasets demonstrate that our method effectively mitigates illumination artifacts while improving rendering quality and quantitative performance over prior approaches. We further validate its benefits for robotic perception through a downstream task.
Abstract:Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perception tasks. Prior approaches based on 2D image enhancement lack reliable supervision and fail to preserve multi-view geometric consistency. To address these limitations, we extend Dark Gaussian Splatting (DarkGS) toward a more accurate and flexible relightable 3D reconstruction framework. First, we eliminate the need for explicit light parameter calibration by jointly optimizing lighting parameters within the Gaussian Splatting framework. Second, we introduce a low-frequency illumination model based on spherical harmonics (SH) to capture spatially varying residual and ambient lighting effects. Third, we incorporate an MLP-based Bidirectional Reflectance Distribution Function (BRDF) to model non-Lambertian reflectance. Experiments on synthetic and real-world datasets demonstrate that our method effectively mitigates illumination artifacts while improving rendering quality and quantitative performance over prior approaches. We further validate its benefits for robotic perception through a downstream task.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2608.14713 [cs.RO]
(or arXiv:2608.14713v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.14713 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 249 cuvinte
Subiecte conexe
SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
arXiv · 21 iul. 2026
Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting
arXiv · 29 iul. 2026
Distilling Privileged Control Barrier Functions into RGB-Only Safety Filters for Dynamic Visual Navigation
arXiv · 30 sept. 2026
PneuTac: Tactile Manipulation with Soft Pneumatic Robots via Unified MPM-Gaussian Splatting Simulation
arXiv · 1 oct. 2026