Burstormer: Burst Image Restoration and Enhancement Transformer

Akshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Khan, Ming-Hsuan Yang

Keywords: Burst super-resolution, multi-frame processing, feature alignment

Abstract:

On a shutter press, modern handheld cameras capture multiple images in rapid succession and merge them to generate a single image. However, individual frames in a burst are misaligned due to inevitable motions and contain multiple degradations. The challenge is to properly align the successive image shots and merge their complimentary information to achieve high-quality outputs. Towards this direction, we propose Burstormer: a novel transformer-based architecture for burst image restoration and enhancement. In comparison to existing works, our approach exploits multi-scale local and non-local features to achieve improved alignment and feature fusion. Our key idea is to enable inter-frame communication in the burst neighborhoods for information aggregation and progressive fusion while modeling the burst-wide context. However, the input burst frames need to be properly aligned before fusing their information. Therefore, we propose an enhanced deformable alignment module for aligning burst features with regards to the reference frame. Unlike existing techniques, the proposed alignment module not only aligns burst features but also exchanges feature information and maintains focused communication with the reference frame through the proposed reference-based feature enrichment mechanism. This additional exchange of information helps in aligning multi-frame features under complex motions. After multi-level alignment and enrichment, we re-emphasize on inter-frame communication within burst frames using a new cyclic burst sampling technique. Finally, the inter-frame information is aggregated using our proposed burst feature fusion module followed by progressive increase in the spatial resolution by shuffling the feature information available in burst frames. The proposed Burstormer outperforms the existing state-of-the-art approaches on three popular tasks of burst super-resolution, burst denoising and burst low-light enhancement. Our codes will
be made public.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/burstormer-burst-image-restoration-and/code)