AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction

Yaopeng Lou, Liao Shen, Tianqi Liu, Jiaqi Li, Zihao Huang, Huiqiang Sun, Zhiguo Cao

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 1 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 depth refinement (MDE depth fused via project-and-sample + 3D U-Net) (ablation)MuGS · DTU small-baselinePSNR: 27.28 -> 27.56Improved
add depth refinement (ablation)MuGS · RealEstate10K large-baselinePSNR: 24.56 -> 24.82Improved
add monocular feature enhancement (ablation)MuGS · DTU small-baselinePSNR: 27.35 -> 27.56Improved
add monocular feature enhancement (ablation)MuGS · RealEstate10K large-baselinePSNR: 24.62 -> 24.82Improved
add reference loss (ablation)MuGS · DTU small-baselinePSNR: 27.52 -> 27.56Improved
add reference loss (ablation)MuGS · RealEstate10K large-baselinePSNR: 24.67 -> 24.82Improved
add depth refinement (ablation)MuGS · RealEstate10K large-baselineLPIPS: 0.161 -> 0.153Improved
add feature enhancement (ablation)MuGS · DTU small-baselineSSIM: 0.955 -> 0.958Improved
replace MVSGaussian with MuGSMVSGaussian · DTU small-baseline (3-view)PSNR: 28.21 -> 29.34Improved
replace MuRF with MuGSMuRF · RealEstate10K large-baselinePSNR: 24.20 -> 24.82Improved
replace MuRF with MuGS in zero-shotMuRF · Zero-shot DTUPSNR: 22.19 -> 22.43Improved
replace MVSGaussian with MuGS on LLFF 3-view LPIPSMVSGaussian · Zero-shot LLFF (3-view)LPIPS: 0.164 -> 0.165Mixed

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