AI Paper Atlas

Research map / 3D vision / Gaussian splatting

CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization

Jiawei Zhang, Jiahe Li, Xiaohan Yu, Lei Huang, Lin Gu, Jin Zheng, Xiao Bai

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 96 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 co-pruning (prune Gaussians that do not match between two fields) (ablation)3DGS · LLFF (3 views)PSNR: 19.22 -> 19.62Improved
add pseudo-view co-regularization (ablation)3DGS · LLFF (3 views)PSNR: 19.22 -> 20.26Improved
combine co-pruning with pseudo-view co-regularization (ablation)CoR-GS · LLFF (3 views)PSNR: 20.26 -> 20.45Improved
add both co-pruning and pseudo-view co-regularization (ablation)3DGS · DTU (3 views)PSNR: 17.65 -> 19.21Improved
apply co-regularization on 360-degree scenes with 12 viewsCoR-GS · Mip-NeRF360 (12 views)LPIPS: 0.415 -> 0.418Mixed
apply CoR-GS with only 3 DTU viewsCoR-GS · DTU (3 views)PSNR: 19.21 vs FreeNeRF 19.92Mixed
add co-regularization (two fields, pseudo views) to 3DGS3DGS · LLFF (3 views) efficiencynumber of Gaussians / FPS: 1.16x10^5 -> 7.85x10^4 points; 318 -> 349 FPSImproved
train two Gaussian fields and render pseudo views3DGS · LLFF (3 views) efficiencytraining time: 2.5min -> 6minHurt
co-pruning distance threshold tau=3 instead of 5 (ablation)CoR-GS · LLFF (3 views)novel view qualityHurt

Later papers that compared with this method

23 later accepted papers report CoR-GS as a baseline in their results tables; 23 of them report a better number on most of the results they share with it.

15 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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