AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GSRecon: Efficient Generalizable Gaussian Splatting for Surface Reconstruction from Sparse Views

Hang Yang, Le Hui, Jianjun Qian, Jin Xie, Jian Yang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 2 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 voxel branch for cross-view aggregation to the baseline (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.68 -> 1.41Improved
use point branch instead of voxel branch (ablation)GSRecon · DTU favorable vs unfavorable setsmean Chamfer distance: favorable 1.05 -> 1.01; unfavorable 1.41 -> 1.64Mixed
combine point and voxel branches (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.41 -> 1.39Improved
add geometry-aware cross-view enhancement (GCE) to baseline (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.68 -> 1.42Improved
add GCE after stage 1 to hybrid aggregation model (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.39 -> 1.32Improved
add GCE after stage 2 only to hybrid aggregation model (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.39 -> 1.38No clear effect
add GCE after both stages 1 and 2 (ablation)GSRecon · DTU unfavorable setmean Chamfer distance: 1.32 -> 1.30Improved
use Gaussian rasterization-based generalizable reconstruction instead of volume-rendering implicit methodsGSRecon · DTU unfavorable viewsreconstruction time (s): 102 -> 0.8Improved
use GSRecon instead of UFOReconGSRecon · DTU unfavorable viewsGPU memory (MB): 7102 -> 8410Hurt
use GSRecon instead of UFOReconGSRecon · DTU unfavorable setmean Chamfer distance: 1.56 -> 1.30Improved
use GSRecon instead of UFORecon on favorable viewsGSRecon · DTU favorable setmean Chamfer distance: 0.99 -> 0.95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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