{"url":"/dataset/stanford-orb","name":"Stanford-ORB","full_name":null,"description_markdown":"We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark. Recent advances in inverse rendering have enabled a wide range of real-world applications in 3D content generation, moving rapidly from research and commercial use cases to consumer devices. While the results continue to improve, there is no real-world benchmark that can quantitatively assess and compare the performance of various inverse rendering methods. Existing real-world datasets typically only consist of the shape and multi-view images of objects, which are not sufficient for evaluating the quality of material recovery and object relighting. Methods capable of recovering material and lighting often resort to synthetic data for quantitative evaluation, which on the other hand does not guarantee generalization to complex real-world environments. We introduce a new dataset of real-world objects captured under a variety of natural scenes with ground-truth 3D scans, multi-view images, and environment lighting. Using this dataset, we establish the first comprehensive real-world evaluation benchmark for object inverse rendering tasks from in-the-wild scenes, and compare the performance of various existing methods.","description_withheld":null,"homepage":"https://stanfordorb.github.io/","introduced_date":"2023-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/stanford-orb-a-real-world-3d-object-inverse","title":"Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark","first_author":"Zhengfei Kuang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Novel View Synthesis","url":"/task/novel-view-synthesis","datasets_with_task":"/datasets/task/novel-view-synthesis"},{"name":"Surface Normals Estimation","url":"/task/surface-normals-estimation","datasets_with_task":"/datasets/task/surface-normals-estimation"},{"name":"Surface Reconstruction","url":"/task/surface-reconstruction","datasets_with_task":"/datasets/task/surface-reconstruction"},{"name":"Depth Prediction","url":"/task/depth-prediction","datasets_with_task":"/datasets/task/depth-prediction"},{"name":"Image Relighting","url":"/task/image-relighting","datasets_with_task":"/datasets/task/image-relighting"},{"name":"Inverse Rendering","url":"/task/inverse-rendering","datasets_with_task":"/datasets/task/inverse-rendering"}],"languages":[],"variants":["Stanford-ORB"],"data_loaders":[{"repo":"https://github.com/StanfordORB/Stanford-ORB","url":"https://github.com/StanfordORB/Stanford-ORB","frameworks":["pytorch"]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-relighting-on-stanford-orb","task":"Image Relighting","dataset_variant":"Stanford-ORB","rows":7,"metrics":["HDR-PSNR","SSIM","LPIPS"],"first_row_in_archive_order":{"model":"Neural-PBIR","paper":"/paper/neural-pbir-reconstruction-of-shape-material","metrics":{"HDR-PSNR":"26.01","LPIPS":"0.023","SSIM":"0.979"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/inverse-rendering-on-stanford-orb","task":"Inverse Rendering","dataset_variant":"Stanford-ORB","rows":7,"metrics":["HDR-PSNR"],"first_row_in_archive_order":{"model":"Neural-PBIR","paper":"/paper/neural-pbir-reconstruction-of-shape-material","metrics":{"HDR-PSNR":"26.01"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/surface-normals-estimation-on-stanford-orb","task":"Surface Normals Estimation","dataset_variant":"Stanford-ORB","rows":7,"metrics":["Cosine Distance"],"first_row_in_archive_order":{"model":"NVDiffRecMC","paper":"/paper/shape-light-material-decomposition-from","metrics":{"Cosine Distance":"0.04"},"code_links":[{"title":"NVlabs/nvdiffrecmc","url":"https://github.com/NVlabs/nvdiffrecmc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/neural-pbir-reconstruction-of-shape-material","title":"Neural-PBIR Reconstruction of Shape, Material, and Illumination","date":"2023-04-26","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/nefii-inverse-rendering-for-reflectance","title":"NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination","date":"2023-03-29","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shape-light-material-decomposition-from","title":"Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising","date":"2022-06-07","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/extracting-triangular-3d-models-materials-and","title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","date":"2021-11-24","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/nerfactor-neural-factorization-of-shape-and","title":"NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination","date":"2021-06-03","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/physg-inverse-rendering-with-spherical","title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting","date":"2021-04-01","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/nerd-neural-reflectance-decomposition-from","title":"NeRD: Neural Reflectance Decomposition from Image Collections","date":"2020-12-07","rows_on_this_dataset":3,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":16,"samples_ran":1,"samples_unverified":15,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}