Research map / Video / Video segmentation and tracking
ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring
Bangrui Jiang, Zhihuai Xie, Zhen Xia, Songnan Li, Shan Liu
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 |
|---|---|---|---|
| replace optical flow alignment with deformable convolution (ablation) | CDVD-TSP · DVD | PSNR: 32.13 -> 32.82 | Improved |
| use dilated convolution for equivalent receptive field in offset prediction (ablation) | Net-1 · DVD | PSNR: 32.82 -> 33.02 | Improved |
| use dilated spatial pyramid block instead of single dilated layer (ablation) | Net-2 · DVD | PSNR: 33.02 -> 33.17 | Improved |
| add gradient branch (ablation) | Net-3 · DVD | PSNR: 33.17 -> 33.31 | Improved |
| add gradient branch (ablation) | Net-3 · DVD | SSIM: 0.9378 -> 0.9395 | Improved |
| increase feature pyramid from 1 to 4 layers (ablation) | ERDN · DVD | PSNR: 31.89 -> 33.31 | Improved |
| increase feature pyramid from 4 to 5 layers (ablation) | ERDN · DVD | PSNR: 33.31 -> 33.20 | Hurt |
| use 5 input frames instead of 3 | ERDN · DVD | PSNR: 32.91 -> 33.31 | Improved |
| use 5 input frames instead of 3 | ERDN · GOPRO | PSNR: 32.20 -> 32.48 | Improved |
| use 5 input frames instead of 3 | ERDN · HFR | PSNR: 32.01 -> 32.14 | Improved |
Closest papers by meaning
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring (AAAI 2022 · similarity 0.89)
- Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training (CVPR 2020 · similarity 0.88)
- Learning Single Image Defocus Deblurring with Misaligned Training Pairs (AAAI 2023 · similarity 0.87)
- Region-Adaptive Dense Network for Efficient Motion Deblurring (AAAI 2020 · similarity 0.87)
- Efficient Video Deblurring Guided by Motion Magnitude (ECCV 2022 · similarity 0.87)
- Understanding Deformable Alignment in Video Super-Resolution (AAAI 2021 · 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.
