AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

Hanzhi Chang, Ruijie Zhu, Wenjie Chang, Mulin Yu, Yanzhe Liang, Jiahao Lu, Zhuoyuan Li, Tianzhu Zhang

AAAI 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 6 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
use 2DGS instead of 3DGS as the feed-forward representation (ablation)MeshSplat · ScannetChamfer distance: 0.3748 -> 0.2948Improved
add Weighted Chamfer Distance loss and normal prediction network to 2DGS (ablation)MeshSplat · ScannetChamfer distance: 0.2948 -> 0.2606Improved
add only one of WCD loss or normal prediction network to 2DGS (ablation)MeshSplat · ScannetChamfer distance: 0.2948 -> 0.2769 and 0.2642 (intermediate rows)Improved
use 2DGS without regularization instead of 3DGS (ablation)Gaussian normals · Rendered normal maps (qualitative)normal qualityHurt
add normal prediction network with NLL loss (ablation)2DGS · Rendered normal maps (qualitative)normal accuracyImproved
replace MVSplat with MeshSplat for depth predictionMeshSplat · Depth predictionAbsRel: 0.1692 -> 0.0910Improved
MeshSplat vs MVSplat for normal predictionMeshSplat · Normal predictionMean angular error: 57.16 -> 33.84Improved
zero-shot transfer from Re10K to ReplicaMeshSplat · Re10K to ReplicaF1: 0.0564 -> 0.0809Improved
MeshSplat vs MVSplat on Re10KMeshSplat · Re10KChamfer distance: 0.4015 -> 0.3566Improved

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