{"url":"/sota/inverse-tone-mapping-on-vds-dataset","task":{"name":"inverse tone mapping","url":"/task/inverse-tone-mapping","note":null},"dataset":{"name":"VDS dataset: Multi exposure stack-based inverse tone mapping","url":"/dataset/vds-dataset"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"For stack based inverse tone mapping","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["HDR-VDP-2","HDR-VDP-3","PU21-PSNR","PU21-SSIM","Reinhard'TMO-PSNR","Kim and Kautz TMO-PSNR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"HDR-VDP-2":null,"HDR-VDP-3":null,"PU21-PSNR":"higher","PU21-SSIM":"higher","Reinhard'TMO-PSNR":"higher","Kim and Kautz TMO-PSNR":"higher"}},"counts":{"rows":9,"rows_with_code":6,"rows_with_paper_page":8,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CEVR","metrics":{"HDR-VDP-2":"59.00","Kim and Kautz TMO-PSNR":"30.04","Reinhard'TMO-PSNR":"34.67"},"uses_additional_data":false,"paper_date":"2023-09-07","paper":"/paper/learning-continuous-exposure-value","paper_url":"https://arxiv.org/abs/2309.03900v1","paper_title":"Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction","code":"https://github.com/skchen1993/2023_CEVR","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DiffHDRsyn","metrics":{"HDR-VDP-2":"58.81","HDR-VDP-3":"8.77","PU21-PSNR":"28.33","PU21-SSIM":"0.9388","Reinhard'TMO-PSNR":"34.12"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/end-to-end-differentiable-learning-to-hdr","paper_url":"https://arxiv.org/abs/2006.15833v2","paper_title":"End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images","code":"https://github.com/JungHeeKim29/DiffHDRsyn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Deep Recursive HDRI","metrics":{"HDR-VDP-2":"57.28","HDR-VDP-3":"8.48","Kim and Kautz TMO-PSNR":"28.02","PU21-PSNR":"25.88","PU21-SSIM":"0.8874","Reinhard'TMO-PSNR":"32.94"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/deep-recursive-hdri-inverse-tone-mapping","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Siyeong_Lee_Deep_Recursive_HDRI_ECCV_2018_paper.html","paper_title":"Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial Networks","code":"https://github.com/Siyeong-Lee/Deep_Recursive_HDRI","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Liu et al.","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,"paper_date":"2020-04-02","paper":"/paper/single-image-hdr-reconstruction-by-learning","paper_url":"https://arxiv.org/abs/2004.01179v1","paper_title":"Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline","code":"https://github.com/alex04072000/SingleHDR","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Deep Chain HDRI","metrics":{"HDR-VDP-2":"56.36","Kim and Kautz TMO-PSNR":"24.54","Reinhard'TMO-PSNR":"30.86"},"uses_additional_data":false,"paper_date":"2018-01-19","paper":"/paper/deep-chain-hdri-reconstructing-a-high-dynamic","paper_url":"http://arxiv.org/abs/1801.06277v1","paper_title":"Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"DrTMO","metrics":{"HDR-VDP-2":"54.33","Kim and Kautz TMO-PSNR":"21.36","Reinhard'TMO-PSNR":"25.49"},"uses_additional_data":false,"paper_date":"2017-11-20","paper":"/paper/deep-reverse-tone-mapping","paper_url":"https://www.npal.cs.tsukuba.ac.jp/~endo/projects/DrTMO/","paper_title":"Deep reverse tone mapping","code":"https://github.com/shleecs/DrTMO_unofficial_pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Santos et al.","metrics":{"HDR-VDP-2":"53.51","Kim and Kautz TMO-PSNR":"18.23","Reinhard'TMO-PSNR":"22.56"},"uses_additional_data":false,"paper_date":"2020-05-15","paper":null,"paper_url":"https://arxiv.org/abs/2005.07335v1","paper_title":"Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Deep Conditional HDRI","metrics":{"HDR-VDP-3":"8.95","PU21-PSNR":"31.15","PU21-SSIM":"0.9537","Reinhard'TMO-PSNR":"35.75"},"uses_additional_data":false,"paper_date":"2024-03-20","paper":"/paper/deep-conditional-hdri-inverse-tone-mapping","paper_url":"https://ieeexplore.ieee.org/abstract/document/10476730","paper_title":"Deep Conditional HDRI: Inverse Tone Mapping via Dual Encoder-Decoder Conditioning Method","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"ExpandNet","metrics":{"HDR-VDP-3":"6.19","PU21-PSNR":"17.42","PU21-SSIM":"0.3612","Reinhard'TMO-PSNR":"23.03"},"uses_additional_data":false,"paper_date":"2018-03-06","paper":"/paper/expandnet-a-deep-convolutional-neural-network","paper_url":"https://arxiv.org/abs/1803.02266v2","paper_title":"ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content","code":"https://github.com/dmarnerides/hdr-expandnet","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}