AI Paper Atlas

Research map / 3D vision / Gaussian splatting

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

Peng Xiang, Liang Han, Hui Zhang, Yu-Shen Liu, Zhizhong Han

AAAI 2026 · 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 anchor-calibrated depth loss L_depth (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 1.51 -> 0.96Improved
add anchor-calibrated depth loss L_depth (ablation)VGGS (PGSR baseline) · TNTF-Score: 0.140 -> 0.174Improved
add relative depth consistency loss L_RDC alone (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 1.51 -> 1.31Improved
add L_RDC on top of L_depth (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 0.96 -> 0.95No clear effect
add L_RDC on top of L_depth (ablation)VGGS (PGSR baseline) · TNTF-Score: 0.174 -> 0.189Improved
add normal prior loss L_normal (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 1.51 -> 1.33Improved
add L_normal to depth and RDC (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 0.95 -> 0.91Improved
add L_normal to depth and RDC (ablation)VGGS (PGSR baseline) · TNTF-Score: 0.189 -> 0.194Improved
use COLMAP Gaussian initialization instead of MASt3R-SfM (ablation)VGGS (PGSR baseline) · DTUChamfer Distance: 0.91 -> 0.95Hurt
use VGGS instead of MAtChaVGGS (PGSR baseline) · DTUChamfer Distance: 1.16 -> 0.91Improved
use VGGS instead of MAtCha at 5 viewsVGGS (PGSR baseline) · TNT 5 viewsF-Score: 0.072 -> 0.076Improved
use VGGS instead of MAtCha for training costVGGS (PGSR baseline) · DTUtraining time: 8 mins -> 2 minsImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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