{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/single-image-hdr-reconstruction-by-learning","title":"Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline","arxiv_id":"2004.01179","date":"2020-04-02","proceeding":"CVPR 2020 6","authors":["Yu-Lun Liu","Wei-Sheng Lai","Yu-Sheng Chen","Yi-Lung Kao","Ming-Hsuan Yang","Yung-Yu Chuang","Jia-Bin Huang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2004.01179v1","url_pdf":"https://arxiv.org/pdf/2004.01179v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"single-image-hdr-reconstruction-by-learning","repo_url":"https://github.com/alex04072000/SingleHDR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hdr-reconstruction","task_name":"HDR Reconstruction"},{"task_slug":"inverse-tone-mapping-1","task_name":"Inverse-Tone-Mapping"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"single-image-based-hdr-reconstruction","task_name":"Single-Image-Based Hdr Reconstruction"},{"task_slug":"inverse-tone-mapping","task_name":"inverse tone mapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/inverse-tone-mapping-on-msu-hdr-video","task":"Inverse-Tone-Mapping","dataset":"MSU HDR Video Reconstruction Benchmark","model":"SingleHDR","rank_in_archive_order":4,"of":9,"metrics":{"HDR-PSNR":"34.2872","HDR-SSIM":"0.9845","HDR-VQM":"0.2630"},"uses_additional_data":false},{"leaderboard":"/sota/inverse-tone-mapping-on-vds-dataset","task":"inverse tone mapping","dataset":"VDS dataset: Multi exposure stack-based inverse tone mapping","model":"Liu et al.","rank_in_archive_order":4,"of":9,"metrics":{"HDR-VDP-2":"56.97","HDR-VDP-3":"8.24","Kim and Kautz TMO-PSNR":"28.00","PU21-PSNR":"25.69","PU21-SSIM":"0.8797","Reinhard'TMO-PSNR":"30.88"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.01179","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}