Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910411918409728 |
|---|---|
| author | Lin, Wenjie Liu, Zhen Jiang, Chengzhi Han, Mingyan Jiang, Ting Liu, Shuaicheng |
| author_facet | Lin, Wenjie Liu, Zhen Jiang, Chengzhi Han, Mingyan Jiang, Ting Liu, Shuaicheng |
| contents | In this paper, we address the Bracket Image Restoration and Enhancement (BracketIRE) task using a novel framework, which requires restoring a high-quality high dynamic range (HDR) image from a sequence of noisy, blurred, and low dynamic range (LDR) multi-exposure RAW inputs. To overcome this challenge, we present the IREANet, which improves the multiple exposure alignment and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM). Specifically, the proposed FFAM incorporates the inter-frame optical flow as guidance to facilitate the deformable alignment and spatial attention modules for better feature alignment. The EFAM further employs the proposed Enhanced Residual Block (ERB) as a foundational component, wherein a unidirectional recurrent network aggregates the aligned temporal features to better reconstruct the results. To improve model generalization and performance, we additionally employ the Bayer preserving augmentation (BayerAug) strategy to augment the multi-exposure RAW inputs. Our experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10358 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation Lin, Wenjie Liu, Zhen Jiang, Chengzhi Han, Mingyan Jiang, Ting Liu, Shuaicheng Computer Vision and Pattern Recognition In this paper, we address the Bracket Image Restoration and Enhancement (BracketIRE) task using a novel framework, which requires restoring a high-quality high dynamic range (HDR) image from a sequence of noisy, blurred, and low dynamic range (LDR) multi-exposure RAW inputs. To overcome this challenge, we present the IREANet, which improves the multiple exposure alignment and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM). Specifically, the proposed FFAM incorporates the inter-frame optical flow as guidance to facilitate the deformable alignment and spatial attention modules for better feature alignment. The EFAM further employs the proposed Enhanced Residual Block (ERB) as a foundational component, wherein a unidirectional recurrent network aggregates the aligned temporal features to better reconstruct the results. To improve model generalization and performance, we additionally employ the Bayer preserving augmentation (BayerAug) strategy to augment the multi-exposure RAW inputs. Our experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods. |
| title | Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.10358 |