AI Paper Atlas

Research map / 3D vision / Gaussian splatting

EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images

Wangbo Yu, Chaoran Feng, Jianing Li, Jiye Tang, Jiashu Yang, Zhenyu Tang, Meng Cao, Xu Jia, Yuchao Yang, Li Yuan, Yonghong Tian

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 63 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 event reconstruction loss L_event to blur loss (ablation)EvaGaussians · Large-scalePSNR: 24.98 -> 25.71Improved
add event reconstruction loss L_event to blur loss (ablation)EvaGaussians · Medium-scalePSNR: 29.10 -> 29.94Improved
add event-assisted depth regularization L_depth (ablation)EvaGaussians · Large-scalePSNR: 25.71 -> 25.54Hurt
add event-assisted depth regularization L_depth (ablation)EvaGaussians · Medium-scaleSSIM: .9098 -> .9139Improved
add intensity reconstruction loss L_int (ablation)EvaGaussians · Large-scalePSNR: 25.54 -> 26.02Improved
add intensity reconstruction loss L_int (ablation)EvaGaussians · Real sceneBRISQUE: 56.17 -> 53.95Improved
add all event losses (L_event, L_depth, L_int) to blur loss only (ablation)EvaGaussians · Medium-scalePSNR: 29.10 -> 30.47Improved
optimize camera poses jointly instead of keeping initial COLMAP poses (ablation)EvaGaussians · Large-scaleATE: 0.3825 -> 0.0489Improved
optimize camera poses jointly (ablation)EvaGaussians · Medium-scaleATE: 0.0598 -> 0.0461Improved
increase number of optimized poses beyond 9 (ablation)EvaGaussians · Large-scalenovel view qualityNo clear effect
increase motion blur from mild to strongEvaGaussians · City blocksPSNR: 26.38 -> 25.04Mixed
use EvaGaussians instead of EDNeRFevent-assisted deblurring · Large-scalePSNR: 24.63 -> 26.02Improved

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