{"url":"/sota/inverse-rendering-on-stanford-orb","task":{"name":"Inverse Rendering","url":"/task/inverse-rendering","note":null},"dataset":{"name":"Stanford-ORB","url":"/dataset/stanford-orb"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Inverse Rendering** is the task of recovering the properties of a scene, such as shape, material, and lighting, from an image or a video. The goal of inverse rendering is to determine the properties of a scene given an observation of it, and to generate new images or videos based on these properties.","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-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-PSNR":"higher"}},"counts":{"rows":7,"rows_with_code":5,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Neural-PBIR","metrics":{"HDR-PSNR":"26.01"},"uses_additional_data":false,"paper_date":"2023-04-26","paper":"/paper/neural-pbir-reconstruction-of-shape-material","paper_url":"https://arxiv.org/abs/2304.13445v5","paper_title":"Neural-PBIR Reconstruction of Shape, Material, and Illumination","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"NVDiffRecMC","metrics":{"HDR-PSNR":"24.43"},"uses_additional_data":false,"paper_date":"2022-06-07","paper":"/paper/shape-light-material-decomposition-from","paper_url":"https://arxiv.org/abs/2206.03380v2","paper_title":"Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising","code":"https://github.com/NVlabs/nvdiffrecmc","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"InvRender","metrics":{"HDR-PSNR":"23.76"},"uses_additional_data":false,"paper_date":"2023-03-29","paper":"/paper/nefii-inverse-rendering-for-reflectance","paper_url":"https://arxiv.org/abs/2303.16617v2","paper_title":"NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination","code":"https://github.com/FuxiComputerVision/Nefii","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"NeRFactor","metrics":{"HDR-PSNR":"23.54"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/nerfactor-neural-factorization-of-shape-and","paper_url":"https://arxiv.org/abs/2106.01970v2","paper_title":"NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination","code":"https://github.com/google/nerfactor","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"NeRD","metrics":{"HDR-PSNR":"23.29"},"uses_additional_data":false,"paper_date":"2020-12-07","paper":"/paper/nerd-neural-reflectance-decomposition-from","paper_url":"https://arxiv.org/abs/2012.03918v4","paper_title":"NeRD: Neural Reflectance Decomposition from Image Collections","code":"https://github.com/cgtuebingen/nerd-neural-reflectance-decomposition","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"NVDiffRec","metrics":{"HDR-PSNR":"22.91"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/extracting-triangular-3d-models-materials-and","paper_url":"https://arxiv.org/abs/2111.12503v5","paper_title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","code":"https://github.com/nvlabs/tiny-cuda-nn","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"PhySG","metrics":{"HDR-PSNR":"21.81"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/physg-inverse-rendering-with-spherical","paper_url":"https://arxiv.org/abs/2104.00674v1","paper_title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":15,"n_samples":16,"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":1,"n_unverified":15,"n_samples":16,"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"}}}