AI Paper Atlas

Research map / 3D vision / 3D generation

EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction

Kanghao Chen, Zixin Zhang, Hangyu Li, Lin Wang, Zeyu Wang

AAAI 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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-based depth loss (ablation)3DGS baseline · Ev-DL3DVPSNR: 16.78 -> 17.92Improved
add event-based depth loss (ablation)3DGS baseline · Ev-DL3DVLPIPS: 0.3596 -> 0.3311Improved
add event-aware diffusion repair (ablation)EvDiff3D with depth loss · Ev-DL3DVPSNR: 17.92 -> 18.86Improved
add event-aware diffusion repair (ablation)EvDiff3D with depth loss · Ev-DL3DVLPIPS: 0.3311 -> 0.3243Improved
add event CLIP feature conditioning (ablation)event-aware diffusion model · Ev-DL3DVPSNR: 0.11 PSNR drop when removedImproved
set lambda_repair between 0.5 and 2.0 (ablation)EvDiff3D · Ev-DL3DV (single sequence)PSNRNo clear effect
increase lambda_repair too large (ablation)EvDiff3D · Ev-DL3DV (single sequence)PSNRHurt
reduce event views to 1/2 of original (ablation)EvDiff3D · Ev-DL3DV (single sequence)PSNR: 18.27 dB at 1/2 viewsMixed
reduce event views below 1/2 (to 1/4) (ablation)EvDiff3D · Ev-DL3DV (single sequence)PSNRHurt
EvDiff3D versus Event3DGSEvent3DGS · Ev-DL3DVPSNR: 16.82 -> 18.86Improved
EvDiff3D versus Event3DGSEvent3DGS · Ev-DL3DVLPIPS: 0.3584 -> 0.3243Improved
add diffusion repair stage (training cost)Event3DGS · Training timeminutes: 15 min -> 40 minHurt

Earlier methods this paper compares with

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