Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910415567454208 |
|---|---|
| author | Liu, Chengxu Wang, Xuan Xu, Xiangyu Tian, Ruhao Li, Shuai Qian, Xueming Yang, Ming-Hsuan |
| author_facet | Liu, Chengxu Wang, Xuan Xu, Xiangyu Tian, Ruhao Li, Shuai Qian, Xueming Yang, Ming-Hsuan |
| contents | Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable motion in the real world but also ignore the tailored handling of various motions in image space. In this paper, we propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative (MISC) Filter. In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter. The MISC Filter first aligns the motion-induced blurring patterns to the motion middle along the predicted flow direction, and then collaboratively filters the aligned image through the predicted kernels, weights, and offsets to generate the output. This design can handle more generalized and complex motion in a spatially differentiated manner. Furthermore, we analyze the relationships between the motion estimation network and the residual reconstruction network. Extensive experiments on four widely used benchmarks demonstrate that our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance. Code is available at https://github.com/ChengxuLiu/MISCFilter |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13153 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring Liu, Chengxu Wang, Xuan Xu, Xiangyu Tian, Ruhao Li, Shuai Qian, Xueming Yang, Ming-Hsuan Image and Video Processing Computer Vision and Pattern Recognition Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable motion in the real world but also ignore the tailored handling of various motions in image space. In this paper, we propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative (MISC) Filter. In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter. The MISC Filter first aligns the motion-induced blurring patterns to the motion middle along the predicted flow direction, and then collaboratively filters the aligned image through the predicted kernels, weights, and offsets to generate the output. This design can handle more generalized and complex motion in a spatially differentiated manner. Furthermore, we analyze the relationships between the motion estimation network and the residual reconstruction network. Extensive experiments on four widely used benchmarks demonstrate that our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance. Code is available at https://github.com/ChengxuLiu/MISCFilter |
| title | Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13153 |