AI Paper Atlas

Research map / 3D vision / Gaussian splatting

CoSurfGS: 3D Surface Gaussian Splatting with Collaborative Distributed Learning for Large-scale Scene Reconstruction

Yuanyuan Gao, Yalun Dai, Hao Li, Weicai Ye, Junyi Chen, Danpeng Chen, Dingwen Zhang, Tong He, Guofeng Zhang, Junwei Han

IJCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 25 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 Model Aggregation Scheme (distillation-based aggregation) (ablation)CoSurfGS · RubblePSNR / SSIM / LPIPS: PSNR 18.07 -> 25.39; SSIM 0.441 -> 0.774; LPIPS 0.584 -> 0.267Improved
add Local Model Compression to local models (ablation)CoSurfGS · Residencememory / PSNR: 874MB -> 475MB; PSNR 22.13 -> 22.23Improved
increase prune percentage from 40% to 80% (ablation)CoSurfGS · Rubblememory / PSNR: 2.5GB -> 1.16GB; PSNR 25.19 -> 24.82Mixed
increase prune percentage from 40% to 60% (ablation)CoSurfGS · RubbleLPIPS: 0.285 -> 0.300Hurt
add geometry loss (no smooth weight) in device training (ablation)device model · RubblePSNR: 25.03 -> 24.36Hurt
add smooth weight to geometry loss (ablation)device model · RubblePSNR: 24.36 -> 24.73Improved
increase partition from (1*1)*4 to (3*3)*4 (ablation)CoSurfGS · RubblePSNR / edge time: PSNR 25.37 -> 24.97; edge 130min -> 43minMixed
train unpartitioned (1*1)*1 whole scene (ablation)CoSurfGS · RubblePSNR: OOMHurt
use distributed device-edge-cloud training vs prior surface methodsCoSurfGS · Mill19 and UrbanScene3D NVSSSIM / PSNR / LPIPS: +0.1, +3.0, and +0.4 in SSIM, PSNR, and LPIPSImproved
use CoSurfGS vs prior mesh methodsPGSR · BlendedMVSF-score: +0.05 in the F-score metric averageImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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