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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add diffusion-generated prior features to the WADT (ablation) | VD-Diff · GoPro | PSNR (dB): 34.38 -> 35.55 | Improved |
| use wavelet transform instead of bilinear down/upsampling (ablation) | VD-Diff · GoPro | PSNR (dB): 34.75 -> 35.55 | Improved |
| add joint training stage of DM and WADT (ablation) | VD-Diff · GoPro | PSNR (dB): 34.92 -> 35.55 | Improved |
| add Wavelet-based Bidirectional Propagation Fuse (WBPF) (ablation) | VD-Diff · GoPro | PSNR (dB): 33.58 -> 35.55 | Improved |
| increase diffusion iteration steps beyond 4 | VD-Diff · GoPro | PSNR (dB) | No clear effect |
| increase inference sequence length beyond 16 frames | VD-Diff · GoPro | PSNR (dB) | No clear effect |
Closest papers by meaning
- Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model (NeurIPS 2024 · similarity 0.89)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.88)
- AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration (ICML 2025 · similarity 0.88)
- Towards Precise Scaling Laws for Video Diffusion Transformers (CVPR 2025 · similarity 0.88)
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention (NeurIPS 2024 · similarity 0.88)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.87)
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.
