Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2405.06918 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929340520857600 |
|---|---|
| author | Zhang, Chi Lin, Mingyuan Zhang, Xiang Jiang, Chenxu Yu, Lei |
| author_facet | Zhang, Chi Lin, Mingyuan Zhang, Xiang Jiang, Chenxu Yu, Lei |
| contents | Super-resolution from motion-blurred images poses a significant challenge due to the combined effects of motion blur and low spatial resolution. To address this challenge, this paper introduces an Event-based Blurry Super Resolution Network (EBSR-Net), which leverages the high temporal resolution of events to mitigate motion blur and improve high-resolution image prediction. Specifically, we propose a multi-scale center-surround event representation to fully capture motion and texture information inherent in events. Additionally, we design a symmetric cross-modal attention module to fully exploit the complementarity between blurry images and events. Furthermore, we introduce an intermodal residual group composed of several residual dense Swin Transformer blocks, each incorporating multiple Swin Transformer layers and a residual connection, to extract global context and facilitate inter-block feature aggregation. Extensive experiments show that our method compares favorably against state-of-the-art approaches and achieves remarkable performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06918 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Super-Resolving Blurry Images with Events Zhang, Chi Lin, Mingyuan Zhang, Xiang Jiang, Chenxu Yu, Lei Computer Vision and Pattern Recognition Super-resolution from motion-blurred images poses a significant challenge due to the combined effects of motion blur and low spatial resolution. To address this challenge, this paper introduces an Event-based Blurry Super Resolution Network (EBSR-Net), which leverages the high temporal resolution of events to mitigate motion blur and improve high-resolution image prediction. Specifically, we propose a multi-scale center-surround event representation to fully capture motion and texture information inherent in events. Additionally, we design a symmetric cross-modal attention module to fully exploit the complementarity between blurry images and events. Furthermore, we introduce an intermodal residual group composed of several residual dense Swin Transformer blocks, each incorporating multiple Swin Transformer layers and a residual connection, to extract global context and facilitate inter-block feature aggregation. Extensive experiments show that our method compares favorably against state-of-the-art approaches and achieves remarkable performance. |
| title | Super-Resolving Blurry Images with Events |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.06918 |