AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis

Xiaobiao Du, Yida Wang, Xin Yu

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 28 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 multi-view regulated learning (ablation)3DGS · Mip-NeRF360PSNR: 28.69 -> 29.26Improved
add cross-ray densification (ablation)3DGS + MVRL · Mip-NeRF360PSNR: 29.26 -> 29.37Improved
add multi-view augmented densification (ablation)3DGS + MVRL + CRD · Mip-NeRF360PSNR: 29.37 -> 29.52Improved
add cross-intrinsic guidance (ablation)3DGS · Mip-NeRF360PSNR: 29.52 -> 29.61Improved
add multi-view regulated learning (ablation)Scaffold-GS · Mip-NeRF360PSNR: 28.84 -> 29.47Improved
add full MVGS components (ablation)Scaffold-GS · Mip-NeRF360PSNR: 28.84 -> 29.82Improved
add multi-view regulated learning (ablation)3D-HGS · Mip-NeRF360PSNR: 29.66 -> 29.94Improved
add full MVGS components (ablation)3D-HGS · Mip-NeRF360PSNR: 29.66 -> 30.21Improved
add MVGSScaffold-GS · Tanks&TemplesPSNR: 23.96 -> 25.54Improved
add MVGS3D-HGS · Deep BlendingPSNR: 29.76 -> 29.74No clear effect
add MVGS3DGS · Mip-NeRF360 Gaussian countNum. Gaussians (x10^6): 1.1 -> 0.8Improved
add MVGS3DGS · Mip-NeRF360 training timeTraining time (h): 0.3 -> 2.4Hurt

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