AI Paper Atlas

Research map / Video / Video generation

Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model

Chen Rao, Guangyuan Li, Zehua Lan, Jiakai Sun, Junsheng Luan, Wei Xing, Lei Zhao, Huaizhong Lin, Jianfeng Dong, Dalong Zhang

ECCV 2024 · Video › Video generation · approach: Efficient video diffusion models · 15 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 diffusion-generated prior features to the WADT (ablation)VD-Diff · GoProPSNR (dB): 34.38 -> 35.55Improved
use wavelet transform instead of bilinear down/upsampling (ablation)VD-Diff · GoProPSNR (dB): 34.75 -> 35.55Improved
add joint training stage of DM and WADT (ablation)VD-Diff · GoProPSNR (dB): 34.92 -> 35.55Improved
add Wavelet-based Bidirectional Propagation Fuse (WBPF) (ablation)VD-Diff · GoProPSNR (dB): 33.58 -> 35.55Improved
increase diffusion iteration steps beyond 4VD-Diff · GoProPSNR (dB)No clear effect
increase inference sequence length beyond 16 framesVD-Diff · GoProPSNR (dB)No clear effect

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