AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Physically Grounded Dual-Opacity Gaussian Splatting for Joint RGB-TIR Reconstruction

Jin Liu, Dabin leng, Jiagang Chen, Haodong Li, Jiguang Li, Zhao Huang, Xiaoshuai Zhang, Zhiwen Zheng, Xingru Huang, Qi Xu

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 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
add dual-opacity rendering (ablation)RaViGS · ThermoNeRF TIRPSNR: 31.617 -> 32.479Improved
add dual-opacity alone to baseline (ablation)3DGS+IR baseline · ThermoNeRF TIRPSNR: 30.910 -> 32.068Improved
add dual-opacity alone to baseline (ablation)3DGS+IR baseline · ThermoNeRF RGBPSNR: 21.878 -> 21.358Hurt
add 3-physics factorization alone (ablation)baseline · ThermoNeRF TIRMAE: 0.606 -> 2.259Hurt
add full set of three componentsRaViGS · ThermoNeRF TIRMAE-ROI: 1.233 -> 1.425Hurt
add physical prior loss (ablation)RaViGS · ThermoNeRF TIRMAE-ROI: 1.912 -> 1.350Improved
add RGB gradient loss and guided TV without physical prior (ablation)RaViGS · ThermoNeRF TIRPSNR: 32.479 -> 29.661Hurt
add all four loss terms vs photometric only (ablation)RaViGS · ThermoNeRF RGBPSNR: 21.641 -> 22.011Improved
use RaViGS instead of OMMGRaViGS · ThermoNeRF TIRPSNR: 32.197 -> 32.479Improved
use RaViGS instead of 3DGS+IRRaViGS · ThermoNeRF RGBPSNR: 21.878 -> 22.011Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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