AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Radiometrically Consistent Gaussian Surfels for Inverse Rendering

Kyu Beom Han, Jaeyoon Kim, Woo Jae Kim, Jinhwan Seo, Sung-eui Yoon

ICLR 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 2 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 radiometric consistency loss (ablation)RadioGS · Indirect-illumination datasetindirect PSNR: 30.0954 -> 32.8832Improved
add radiometric consistency loss when training views reduced to 25% (ablation)RadioGS · Indirect-illumination dataset (25% views)indirect PSNR: 27.89 -> 32.71Improved
detach gradient through ray-traced surfels (ablation)RadioGS · TensoIRNVS PSNR / relighting PSNR: 37.252 -> 37.858 NVSImproved
use differentiable ray-traced indirect radiance instead of frozen precomputed (ablation)RadioGS · TensoIRNVS PSNR: 35.547 -> 37.858Improved
add indirect radiance from surfels instead of split-sum (ablation)RadioGS · TensoIRalbedo PSNR: 27.471 -> 31.048Improved
increase number of supervised surfels N_g from 1024 to 8192 (ablation)RadioGS · TensoIRrelight PSNR: 32.0569 -> 32.1294Improved
increase secondary ray samples N_s from 64 to 128 (ablation)RadioGS · TensoIRNVS/relight PSNRNo clear effect
use finetuning-based relighting instead of ray-tracing relightingRadioGS · TensoIRrelight PSNR and render time: 32.09 -> 31.41 PSNR; 38.64 -> 5.902 msMixed
add physically-based radiometric loss during initialization (ablation)RadioGS · TensoIRPSNRImproved
RadioGS vs best baselineRadioGS · Synthetic4Relightroughness MSE: 0.008 -> 0.011Hurt

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