AI Paper Atlas

Research map / 3D vision / Gaussian splatting

CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images

Jungho Lee, Donghyeong Kim, Dogyoon Lee, Suhwan Cho, Minhyeok Lee, Wonjoon Lee, Taeoh Kim, Dongyoon Wee, Sangyoun Lee

ICCV 2025 · 3D vision › Gaussian splatting · approach: Deformable 4D 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
add rigid body transformation to Mip-Splatting baseline (ablation)Mip-Splatting · Deblur-NeRF real-worldPSNR: 21.87 -> 27.19Improved
add CMR transformation on top of rigid motion (ablation)CoMoGaussian · Deblur-NeRF real-worldPSNR: 27.19 -> 27.74Improved
add orthogonality loss on CMR rotation (ablation)CoMoGaussian · Deblur-NeRF real-worldLPIPS: 0.0878 -> 0.0822Improved
replace linear interpolation / cubic B-spline physical-space trajectories with latent-space neural ODE (ablation)CoMoGaussian · Deblur-NeRF real-worldPSNR: 21.69 -> 27.85Improved
replace MLP or GRU with neural ODE for latent features (ablation)CoMoGaussian · Deblur-NeRF real-worldLPIPS: 0.1010 (MLP), 0.0988 (GRU) -> 0.0822Improved
add CMR so fewer poses are needed (ablation)CoMoGaussian · Deblur-NeRF real-worldPSNR: 27.57 (rigid only, N=13) -> 27.85 (rigid+CMR, N=9)Improved
increase number of poses N for rigid-only trajectory (ablation)Rigid only · Deblur-NeRF real-worldPSNR: 26.60 -> 27.57 (N=5 to 13)Improved
increase poses N beyond 9 with CMR (ablation)Rigid + CMR · Deblur-NeRF real-worldPSNR: 27.85 (N=9) vs 27.89 (N=10) vs 27.81 (N=13)No clear effect
remove orthogonal regularization (ablation)CoMoGaussian · Deblur-NeRF real-worldvisual detailImproved
apply deblurring method on sharp imagesCoMoGaussian vs Deblurring 3DGS · NeRF-LLFFPSNR: CoMoGaussian 27.56 vs Mip-Splatting 27.71; Deblurring 3DGS 17.42Mixed
CoMoGaussian vs other deblurring 3DGS methods on training timeCoMoGaussian · Deblur-NeRF real-worldTraining time (hours): 0.20 (Deblurring 3DGS) -> 1.33Hurt

Later papers that compared with this method

1 later accepted paper reports CoMoGaussian as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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