AI Paper Atlas

Research map / 3D vision / Gaussian splatting

3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction

Takeshi Noda, Yu-Shen Liu, Zhizhong Han

CVPR 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 self-constrained prior f^t (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.56 -> 0.50Improved
add opacity constraint L_SCP (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.53 -> 0.50Improved
update prior from f^0 to f^1 and f^2 (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.54 -> 0.52 -> 0.50Improved
add Gaussian outlier removal (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.53 -> 0.50Improved
add Gaussian projection toward surface (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.51 -> 0.50Improved
shrink bandwidth progressively 1, 0.5, 0.25 (ablation)Gaussian splatting surface model · DTUChamfer distance: 0.54 -> 0.53 -> 0.51 -> 0.50Improved
self-constrained prior vs PGSRGaussian splatting surface model · DTUChamfer distance: 0.53 -> 0.50Improved
self-constrained prior vs PGSRGaussian splatting surface model · Tanks and TemplesF1-score: 0.50 -> 0.51No clear effect
self-constrained prior vs 3DGS on novel view synthesisGaussian splatting surface model · Mip-NeRF 360 (outdoor scenes)PSNR: 24.64 -> 24.81No clear effect
self-constrained prior vs 2DGSGaussian splatting surface model · NeRF-SyntheticCD_L1 x100: 2.26 -> 1.87Improved
add prior-based method but longer training time vs 2DGSGaussian splatting surface model · DTUtraining time: 19.2min -> 42minHurt

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