Exposure Bracketing Is All You Need For A High-Quality Image
Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, Wangmeng Zuo
Abstract
It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposure, or multi-exposure images) have made significant progress in addressing this issue, they typically focus on specific restoration or enhancement problems, and do not fully explore the potential of utilizing multiple images. Motivated by the fact that multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution, we propose to utilize exposure bracketing photography to get a high-quality image by combining these tasks in this work. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data and then adapts it to real-world unlabeled images. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed. Moreover, we construct a data simulation pipeline to synthesize pairs and collect real-world images from 200 nighttime scenarios. Experiments on both datasets show that our method performs favorably against the state-ofthe-art multi-image processing ones. Code and datasets are available at https: //github.com/cszhilu1998/BracketIRE.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure Sequences cites Exploring CLIP for Assessing the Look and Feel of Images
- DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure Sequences cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- Intriguing Findings of Frequency Selection for Image Deblurring cites Rethinking Coarse-to-Fine Approach in Single Image Deblurring
- Dynamic Exposure Burst Image Restoration cites BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- Dynamic Exposure Burst Image Restoration cites Burst Image Restoration and Enhancement
Cited by top-tier papers2
Builds on39
- Exploring CLIP for Assessing the Look and Feel of ImagesJianyi Wang, Kelvin C. K. Chan, Chen Change LoyAAAI 2023 · 1,208 citations
- Rethinking Coarse-to-Fine Approach in Single Image DeblurringSung-Jin Cho, Seo-Won Ji, Jun-Pyo Hong, Seung-Won Jung et al.ICCV 2021 · 799 citations
- BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and AlignmentKelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change LoyCVPR 2022 · 522 citations
- Intriguing Findings of Frequency Selection for Image DeblurringXintian Mao, Yiming Liu, Fengze Liu, Qingli Li et al.AAAI 2023 · 249 citations
- Burst Image Restoration and EnhancementAkshay Dudhane, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan et al.CVPR 2022 · 99 citations
Related papers
- Learning a Reinforced Agent for Flexible Exposure Bracketing SelectionZhouxia Wang, Jiawei Zhang, Mude Lin, Jiong Wang et al.CVPR 2020
- Self-Supervised Image Restoration with Blurry and Noisy PairsZhilu Zhang, Rongjian Xu, Ming Liu, Zifei Yan et al.NeurIPS 2022 · 30 citations
- Dancing in the Dark: A Benchmark towards General Low-light Video EnhancementHuiyuan Fu, Wenkai Zheng, Xicong Wang, Jiaxuan Wang et al.ICCV 2023 · 37 citations
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic ScenesZhilu Zhang, Haoyu Wang, Shuai Liu, Xiaotao Wang et al.ICLR 2024 · 16 citations
- Gated Multi-Resolution Transfer Network for Burst Restoration and EnhancementNancy Mehta, Akshay Dudhane, Subrahmanyam Murala, Syed Waqas Zamir et al.CVPR 2023
