{"url":"/dataset/spaces","name":"Spaces","full_name":null,"description_markdown":"We introduce our new dataset, Spaces, to provide a more challenging shared dataset for future view synthesis research.\r\nSpaces consists of 100 indoor and outdoor scenes, captured using a 16-camera rig. \r\nFor each scene, we captured image sets at 5-10 slightly different rig positions (within ∼10cm of each other). \r\nThis jittering of the rig position provides a flexible dataset for view synthesis, as we can mix views from different rig positions for the same scene during training. \r\nWe calibrated the intrinsics and the relative pose of the rig cameras using a standard structure from motion approach, using the nominal rig layout as a prior. \r\nWe corrected exposure differences . \r\nFor our main experiments we undistort the images and downsample them to a resolution of 800 × 480.\r\nWe use 90 scenes from the dataset for training and hold out 10 for evaluation.","description_withheld":null,"homepage":"https://github.com/augmentedperception/spaces_dataset","introduced_date":"2019-06-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/deepview-view-synthesis-with-learned-gradient-1","title":"DeepView: View Synthesis with Learned Gradient Descent","first_author":"John Flynn","url":null},"license":{"name":"CC BY NC 4.0","url":"https://github.com/augmentedperception/spaces_dataset/blob/master/data/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Novel View Synthesis","url":"/task/novel-view-synthesis","datasets_with_task":"/datasets/task/novel-view-synthesis"},{"name":"Generalizable Novel View Synthesis","url":"/task/generalizable-novel-view-synthesis","datasets_with_task":"/datasets/task/generalizable-novel-view-synthesis"}],"languages":[],"variants":["Spaces"],"data_loaders":[],"num_papers_in_archive":32,"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."}