AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors

Liang Han, Bangcai Wei, Junsheng Zhou, Yushen Liu, Zhizhong Han

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 normal prior loss L_normal (ablation)3DGS rendering baseline · DTU ablation (3 views)mean CD: 2.79 -> 2.28Improved
add opacity decay strategy (ablation)3DGS with L_normal · DTU ablation (3 views)mean CD: 2.28 -> 1.55Improved
add depth propagation constraint L_dp (ablation)3DGS with L_normal and O.D. · DTU ablation (3 views)mean CD: 1.55 -> 1.13Improved
add abnormal depth edge smoothing L_ds (ablation)3DGS with L_normal and O.D. · DTU ablation (3 views)mean CD: 1.55 -> 1.38Improved
add L_ds on top of L_dp (ablation)full method · DTU ablation (3 views)mean CD: 1.13 -> 1.02Improved
add L_dp on top of L_ds (ablation)full method · DTU ablation (3 views)mean CD: 1.38 -> 1.02Improved
raise propagation iterations from 4 to 10 (ablation)depth propagation · DTU propagation iterationsCD: 1.126 -> 1.021Improved
raise propagation iterations beyond 10 (ablation)depth propagation · DTU propagation iterationsCD: 1.021 -> 1.032No clear effect
use Metric3Dv2 instead of Omnidata normal prior (ablation)Ours · DTU normal priorCD: 1.14 -> 1.02Improved
use Metric3Dv2 instead of StableNormal normal prior (ablation)Ours · DTU normal priorCD: 1.05 -> 1.02Improved
use MASt3R dense point cloud initializationOurs · DTU (3 small-overlap views, 15 scenes)mean CD: 1.02 -> 0.85Improved
use Ours instead of MAtCha3DGS sparse reconstruction · Tanks and Temples (4 scenes), 20 viewsF1: 0.218 -> 0.293Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 7 of 7 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