AI Paper Atlas

Research map / 3D vision / Gaussian splatting

$L^{2}DGS$: Low-Light Dynamic Gaussian Splatting

Ashish Kumar, Rajagopalan N Ambasamduram

CVPR 2026 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting

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 Occlusion-Disocclusion Network (OCD-Net) (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 13.36 -> 14.68Improved
add BAFE-Net to enhance Brightness Attenuation Features (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 6.14 -> 14.68Improved
add signal amplification regularizer (maximize Lw) (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 6.99 -> 14.68Improved
add exposure regularizer on reflectance (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 7.65 -> 14.68Improved
add SSIM term to photometric loss (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 13.20 -> 14.68Improved
add edge-aware depth smoothness loss (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 14.27 -> 14.68Improved
add SASR gradient regularizers on B1 and B2 (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 14.56 -> 14.68Improved
also maximize reflectance Rw (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 14.68 -> 14.57No clear effect
maximize Rw instead of Lw (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 14.68 -> 6.89Hurt
fix B1 = 1 or B2 = 1 instead of learned BAFs (ablation)L2DGS · Synthetic average (Sriracha, Creeper, Mochi, Apple), overallPSNR: 14.68 -> 12.46 (B1=1), 12.54 (B2=1)Hurt
compare L2DGS against baselines on Handwavy synthetic sceneL2DGS · Handwavy (synthetic, overall)PSNR: 11.72 vs 12.78 (LLNeRF)Mixed
L2DGS vs best baseline on Mochi dynamic-aware reconstructionL2DGS · Mochi (synthetic, overall)PSNR: 14.95 -> 17.61Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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