Exposure Bracketing Is All You Need For A High-Quality Image

Authors: Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan, Wangmeng Zuo

ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on both datasets show that our method performs favorably against the state-of-the-art multi-image processing ones. Code and datasets are available at https: //github.com/cszhilu1998/Bracket IRE. ... We conduct extensive experiments, which show that the proposed method achieves state-of-the-art performance in comparison with other multi-image processing ones.
Researcher Affiliation Academia Zhilu Zhang, Shuohao Zhang, Renlong Wu, Zifei Yan , Wangmeng Zuo Harbin Institute of Technology, Harbin, China EMAIL, EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes the methodology and network architecture using textual descriptions and figures, but no explicit pseudocode or algorithm blocks are provided.
Open Source Code Yes Code and datasets are available at https: //github.com/cszhilu1998/Bracket IRE.
Open Datasets Yes Code and datasets are available at https: //github.com/cszhilu1998/Bracket IRE. ... We start with HDR videos from Froehlich et al. (Froehlich et al., 2014)1 to construct the simulation pipeline. ... 1The dataset is licensed under CC BY and is publicly available at the site.
Dataset Splits Yes Finally, we obtain 1,335 data pairs from 35 scenes. 1,045 pairs from 31 scenes are used for training, and the remaining 290 pairs from the other 4 scenes are used for testing. ... A total of 200. 100 scenes are used for training and the other 100 are used for evaluation.
Hardware Specification Yes All experiments are conducted using Py Torch (Paszke et al., 2019) on a single Nvidia RTX A6000 (48GB) GPU.
Software Dependencies No The paper mentions 'Py Torch (Paszke et al., 2019)' but does not specify a version number for it or any other key software libraries or dependencies required for reproduction.
Experiment Setup Yes The batch size is set to 8. The input patch size is 128 128 and 64 64 for Bracket IRE and Bracket IRE+ tasks, respectively. We adopt Adam W (Loshchilov & Hutter, 2017) optimizer with β1 = 0.9 and β2 = 0.999. Models are trained for 400 epochs ( 60 hours) on synthetic images and fine-tuned for 10 epochs ( 2.6 hours) on real-world ones, with the initial learning rate of 10 4 and 7.5 10 5, respectively. Cosine annealing strategy (Loshchilov & Hutter, 2016) is employed to decrease the learning rates to 10 6. r is randomly selected from {1, 2, 3}. λself is set to 1.