Papers › Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

2 Apr 2020CVPR 2020 6arXiv:2004.01179archive 2025-07-28

Yu-Lun Liu, Wei-Sheng Lai, Yu-Sheng Chen, Yi-Lung Kao, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

alex04072000/SingleHDR officialmentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HDR ReconstructionInverse-Tone-MappingQuantizationSingle-Image-Based Hdr Reconstructioninverse tone mapping

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark SingleHDR HDR-PSNR 34.2872 #4 of 9 Archive leaderboard report
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark SingleHDR HDR-SSIM 0.9845 #4 of 9 Archive leaderboard report
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark SingleHDR HDR-VQM 0.2630 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. HDR-VDP-2 56.97 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. HDR-VDP-3 8.24 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. Kim and Kautz TMO-PSNR 28.00 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. PU21-PSNR 25.69 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. PU21-SSIM 0.8797 #4 of 9 Archive leaderboard report
inverse tone mapping VDS dataset: Multi exposure stack-based inverse tone mapping Liu et al. Reinhard'TMO-PSNR 30.88 #4 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections