{"url":"/dataset/si-hdr","name":"SI-HDR","full_name":"Single-image high dynamic range dataset","description_markdown":"The dataset consists of 181 HDR images. Each image includes: 1) a RAW exposure stack, 2) an HDR image, 3) simulated camera images at two different exposures 4) Results of 6 single-image HDR reconstruction methods: Endo et al. 2017, Eilertsen et al. 2017, Marnerides et al. 2018, Lee et al. 2018, Liu et al. 2020, and Santos et al. 2020\r\n\r\n# Project web page\r\n\r\nMore details can be found at: <https://www.cl.cam.ac.uk/research/rainbow/projects/sihdr_benchmark/>\r\n\r\n# Overview\r\n\r\nThis dataset contains 181 RAW exposure stacks selected to cover a wide range of image content and lighting conditions. Each scene is composed of 5 RAW exposures and merged into an HDR image using the estimator that accounts photon noise [3] (code at [HDRutils](https://github.com/gfxdisp/HDRutils)). A simple color correction was applied using a reference white point and all merged HDR images were resized to 1920×1280 pixels.\r\n\r\nThe primary purpose of the dataset was to compare various single image HDR (SI-HDR) methods [1]. Thus, we selected a wide variety of content covering nature, portraits, cities, indoor and outdoor, daylight and night scenes. After merging and resizing, we simulated captures by applying a custom CRF and added realistic camera noise based on estimated noise parameters of *Canon 5D Mark III*.\r\n\r\nThe simulated captures were inputs to six selected SI-HDR methods. You can view the reconstructions of various methods for select scenes on our [interactive viewer](https://www.cl.cam.ac.uk/research/rainbow/projects/sihdr_benchmark/). For the remaining scenes, please download the appropriate zip files. We conducted a rigorous pairwise comparison experiment on these images to find that widely-used metrics did not correlate well with subjective data. We then proposed an improved evaluation protocol for SI-HDR [1].\r\n\r\nIf you find this dataset useful, please cite [1].\r\n\r\n# References\r\n\r\n[1] Param Hanji, Rafał K. Mantiuk, Gabriel Eilertsen, Saghi Hajisharif, and Jonas Unger. 2022. “Comparison of single image hdr reconstruction methods — the caveats of quality assessment.” In *Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings (SIGGRAPH ’22 Conference Proceedings)*. [Online]. Available: <https://www.cl.cam.ac.uk/research/rainbow/projects/sihdr_benchmark/>\r\n\r\n[2] Gabriel Eilertsen, Saghi Hajisharif, Param Hanji, Apostolia Tsirikoglou, Rafał K. Mantiuk, and Jonas Unger. 2021. “How to cheat with metrics in single-image HDR reconstruction.” In *Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops*. 3998–4007.\r\n\r\n[3] Param Hanji, Fangcheng Zhong, and Rafał K. Mantiuk. 2020. “Noise-Aware Merging of High Dynamic Range Image Stacks without Camera Calibration.” In *Advances in Image Manipulation (ECCV workshop)*. Springer, 376–391. [Online]. Available: <https://www.cl.cam.ac.uk/research/rainbow/projects/noise-aware-merging/>","description_withheld":null,"homepage":"https://www.repository.cam.ac.uk/items/c02ccdde-db20-4acd-8941-7816ef6b7dc7","introduced_date":"2022-07-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/comparison-of-single-image-hdr-reconstruction","title":"Comparison of single image HDR reconstruction methods — the caveats of quality assessment","first_author":"Param Hanji","url":null},"license":{"name":"Creative Commons 4.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Single-Image-Based Hdr Reconstruction","url":"/task/single-image-based-hdr-reconstruction","datasets_with_task":"/datasets/task/single-image-based-hdr-reconstruction"},{"name":"HDR Reconstruction","url":"/task/hdr-reconstruction","datasets_with_task":"/datasets/task/hdr-reconstruction"},{"name":"Single-shot HDR Reconstruction","url":"/task/single-shot-hdr-reconstruction","datasets_with_task":"/datasets/task/single-shot-hdr-reconstruction"}],"languages":[],"variants":["SI-HDR"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}