{"url":"/dataset/ibims-1","name":"IBims-1","full_name":"Independent benchmark images and matched scans v1","description_markdown":"iBims-1 (independent Benchmark images and matched scans - version 1) is a new high-quality RGB-D dataset, especially designed for testing single-image depth estimation (SIDE) methods. A customized acquisition setup, composed of a digital single-lens reflex (DSLR) camera and a high-precision laser scanner was used to acquire high-resolution images and highly accurate depth maps of diverse indoors scenarios.\r\n\r\nCompared to related RGB-D datasets, iBims-1 stands out due to a very low noise level, sharp depth transitions, no occlusions, and high depth ranges.\r\n\r\nOur dataset consists of the following components:\r\n\r\nCore dataset:\r\n\r\n- 100 RGB-D image pairs of various indoor scenes in high- and low resolution\r\n- Masks for invalid, transparent and planar regions (tables, floors, walls)\r\n- Masks for distinct depth transitions\r\n- Camera calibration parameters\r\n\r\n\r\nAuxiliary dataset:\r\n- 56 different color and geometric augmentations for each image of the core dataset\r\n- Additional hand-held images for testing MVS methods\r\n- Images of printed patterns and photos posted on a wall to assess performance of textured planar surfaces\r\n- Several RGB-D image sequences of static scenes with varying illumation\r\n\r\nSource: [Evaluation of CNN-based Single-Image Depth Estimation Methods](https://arxiv.org/pdf/1805.01328v1.pdf)\r\n\r\nImage source: [https://arxiv.org/pdf/1805.01328v1.pdf](https://arxiv.org/pdf/1805.01328v1.pdf)","description_withheld":null,"homepage":"https://www.bgu.tum.de/lmf/ibims1/","introduced_date":"2018-05-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluation-of-cnn-based-single-image-depth","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","first_author":"Tobias Koch","url":null},"license":{"name":"Custom","url":"https://www.bgu.tum.de/lmf/ibims1/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","datasets_with_task":"/datasets/task/monocular-depth-estimation"},{"name":"Surface Normals Estimation","url":"/task/surface-normals-estimation","datasets_with_task":"/datasets/task/surface-normals-estimation"}],"languages":[],"variants":["IBims-1"],"data_loaders":[],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/monocular-depth-estimation-on-ibims-1","task":"Monocular Depth Estimation","dataset_variant":"IBims-1","rows":4,"metrics":["ORD","D3R","RMSE","δ1.25","absolute relative error"],"first_row_in_archive_order":{"model":"Miangoleh et al. (SGR)","paper":"/paper/boosting-monocular-depth-estimation-models-to","metrics":{"D3R":"0.3222","ORD":"0.3938","RMSE":"0.1598","δ1.25":"0.6390"},"code_links":[{"title":"compphoto/BoostingMonocularDepth","url":"https://github.com/compphoto/BoostingMonocularDepth"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/surface-normals-estimation-on-ibims-1","task":"Surface Normals Estimation","dataset_variant":"IBims-1","rows":2,"metrics":["% < 11.25","% < 22.5","% < 30","Mean"],"first_row_in_archive_order":{"model":"Marigold + E2E FT(zero-shot)","paper":"/paper/fine-tuning-image-conditional-diffusion","metrics":{"% < 11.25":"69.9","Mean":"15.8"},"code_links":[{"title":"VisualComputingInstitute/diffusion-e2e-ft","url":"https://github.com/VisualComputingInstitute/diffusion-e2e-ft"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/fine-tuning-image-conditional-diffusion","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","date":"2024-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":16,"samples_unverified":1,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scaledepth-decomposing-metric-depth","title":"ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation","date":"2024-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/metric3d-v2-a-versatile-monocular-geometric-1","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","date":"2024-03-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/boosting-monocular-depth-estimation-models-to","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","date":"2021-05-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":22,"samples_ran":21,"samples_unverified":1,"pointer_only_for_licence":19,"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."}