AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes

Kang Du, Xue Liao, Junpeng Xia, Chaozheng Guo, Yi Gu, Yirui Guan, Duotun Wang, Sheng Huang, Zeyu Wang

CVPR 2026 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 0 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
use explicit illumination modeling (LumiGauss) instead of implicit (WildGaussians)Gaussian-based reconstruction · UAVLight FootbridgePSNR: 17.45 -> 20.89Improved
use explicit illumination modeling (LumiGauss) instead of implicit (WildGaussians)Gaussian-based reconstruction · UAVLight IndustrialPSNR: 16.63 -> 20.34Improved
use explicit illumination modeling (LumiGauss) instead of implicit (WildGaussians)Gaussian-based reconstruction · UAVLight TownPSNR: 23.95 -> 23.59No clear effect
use Gaussian-based GS-W instead of NeRF-Wimplicit appearance modeling · UAVLight TownPSNR: 19.63 -> 22.27Improved
use LumiGauss instead of NeRF-OSR (Gaussian instead of NeRF explicit)explicit illumination modeling · UAVLight Towntraining time (hr): 179 hr -> 36 hrImproved

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