Papers › A Two-stage Deep Network for High Dynamic Range Image Reconstruction

A Two-stage Deep Network for High Dynamic Range Image Reconstruction

19 Apr 2021arXiv:2104.09386archive 2025-07-28

SMA Sharif, Rizwan Ali Naqvi, Mithun Biswas, Kim Sungjun

Mapping a single exposure low dynamic range (LDR) image into a high dynamic range (HDR) is considered among the most strenuous image to image translation tasks due to exposure-related missing information. This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image without knowing hardware information, including camera response function (CRF) and exposure settings. Therefore, we aim to perform image enhancement task like denoising, exposure correction, etc., in the first stage. Additionally, the second stage of our deep network learns tone mapping and bit-expansion from a convex set of data samples. The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference. Apart from that, we collected an LDR image dataset incorporating different camera systems. The evaluation with our collected real-world LDR images illustrates that the proposed method can reconstruct plausible HDR images without presenting any visual artefacts. Code available: https://github. com/sharif-apu/twostageHDR_NTIRE21.

PaperPDFCode

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

Code

sharif-apu/twostageHDR_NTIRE21 officialmentioned in papermentioned on GitHubpytorch report
xypu98/two-stage-HDR-video mentioned on GitHubpytorch 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

DenoisingExposure CorrectionImage EnhancementImage ReconstructionImage-to-Image TranslationInverse-Tone-MappingTone MappingTranslationVocal Bursts Intensity PredictionVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark twostageHDR HDR-PSNR 31.6717 #9 of 9 Archive leaderboard report
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark twostageHDR HDR-SSIM 0.9884 #9 of 9 Archive leaderboard report
Inverse-Tone-Mapping MSU HDR Video Reconstruction Benchmark twostageHDR HDR-VQM 0.1350 #9 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