CVApr 16, 2024

Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation

arXiv:2404.10358v12 citationsh-index: 7
Originality Incremental advance
AI Analysis

This work addresses image quality enhancement for photography and computational imaging applications, representing an incremental improvement with novel modules for alignment and aggregation.

The paper tackles the Bracket Image Restoration and Enhancement task by proposing IREANet, a framework that restores high-quality HDR images from noisy, blurred, and low dynamic range multi-exposure RAW inputs, achieving state-of-the-art performance in experiments.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes