{"url":"/dataset/wildlight","name":"wildlight","full_name":null,"description_markdown":"Multi-view image dataset of seven objects under indoor lighting, for the purpose of multi-view 3D reconstruction and inverse rendering. Around half images are taken under indoor environment lighting only, and the other half are also under a flashlight co-located with camera centre. The co-located flashlight images are for material/BSDF reconstruction.\r\n\r\nFour out of seven objects are synthesised in blender and has geometry ground truth. The other three are real-world objects captured by an iPhone and do not have ground truth.","description_withheld":null,"homepage":"https://github.com/za-cheng/WildLight","introduced_date":"2023-03-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/wildlight-in-the-wild-inverse-rendering-with","title":"WildLight: In-the-wild Inverse Rendering with a Flashlight","first_author":"Ziang Cheng","url":null},"license":{"name":"Public Domain","url":null},"modalities":[],"tasks":[],"languages":[],"variants":["wildlight"],"data_loaders":[],"num_papers_in_archive":3,"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."}