{"url":"/dataset/silvr","name":"SILVR","full_name":"A Synthetic Immersive Large-Volume Plenoptic Dataset","description_markdown":"We present _SILVR_, a dataset of light field images for six-degrees-of-freedom\r\nnavigation in large fully-immersive volumes. The _SILVR_ dataset is short for\r\n_\"**S**ynthetic **I**mmersive **L**arge-**V**olume **R**ay\"_ dataset.\r\n\r\n## Properties\r\nOur dataset exhibits the following properties:\r\n\r\n - **synthetic**: Rendered using Blender 3.0 with Cycles, the images are\r\n   perfect and do not need any calibration. Camera positions and lens\r\n   configurations are known exactly and provided in the corresponding JSON\r\n   files.\r\n - **large interpolation volume**: The camera configurations span a\r\n   relatively large volume (a couple of meters in diameter).\r\n - **large field of view**: In order to maximize the _interpolation volume_\r\n   (a.k.a: the walkable volume of light), the images are rendered using fisheye\r\n   lenses with a field of view of 180°.\r\n - **immersive**: Thanks to the large field of view and positioning of the\r\n   viewpoints, every point within the interpolation volume has a full panoramic\r\n   field of view of light information available.\r\n - **realism**: The selected scenes have reasonable realism.\r\n - **depth maps**: As the images are computer-generated renders, we provide\r\n   depth maps for every image.\r\n - **specularities** and **reflections**: The scenes exhibit some specularities\r\n   or reflections, including mirrors. Reflections and mirrors always have the\r\n   depth of the surface, and not the apparent depth of the reflections.\r\n - **volumetrics**: Some volumetrics are also present (fire, smoke, fog) in the\r\n   `garden` scene.\r\n - **densly rendered**: The camera setup is rather dense (around 10cm spacing\r\n   between cameras).","description_withheld":null,"homepage":"https://idlabmedia.github.io/large-lightfields-dataset/","introduced_date":"2022-04-20","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-BY","url":"https://github.com/IDLabMedia/large-lightfields-dataset/blob/main/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"}],"languages":[],"variants":["SILVR"],"data_loaders":[],"num_papers_in_archive":2,"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."}