{"url":"/dataset/sprites","name":"Sprites","full_name":"2D Video Game Character Sprites","description_markdown":"The **Sprites** dataset contains 60 pixel color images of animated characters (sprites). There are 672 sprites, 500 for training, 100 for testing and 72 for validation. Each sprite has 20 animations and 178 images, so the full dataset has 120K images in total. There are many changes in the appearance of the sprites, they differ in their body shape, gender, hair, armor, arm type, greaves, and weapon.\r\n\r\nSource: [Challenges in Disentangling Independent Factors of Variation](https://arxiv.org/abs/1711.02245)","description_withheld":null,"homepage":"https://github.com/YingzhenLi/Sprites","introduced_date":"2015-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-visual-analogy-making","title":"Deep Visual Analogy-Making","first_author":"Scott E. Reed","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Imputation","url":"/task/imputation","datasets_with_task":"/datasets/task/imputation"},{"name":"Disentanglement","url":"/task/disentanglement","datasets_with_task":"/datasets/task/disentanglement"}],"languages":[],"variants":["Colored dSprites","Sprites"],"data_loaders":[{"repo":"https://github.com/nmichlo/disent","url":"https://github.com/nmichlo/disent","frameworks":["pytorch"]},{"repo":"https://github.com/YingzhenLi/Sprites","url":"https://github.com/YingzhenLi/Sprites","frameworks":[]}],"num_papers_in_archive":52,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/imputation-on-sprites","task":"Imputation","dataset_variant":"Sprites","rows":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"GP-VAE (B-NLST)","paper":"/paper/seq2tens-an-efficient-representation-of","metrics":{"MSE":"0.002"},"code_links":[{"title":"tgcsaba/seq2tens","url":"https://github.com/tgcsaba/seq2tens"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-colored-dsprites","task":"Video Prediction","dataset_variant":"Colored dSprites","rows":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper":"/paper/disentangling-representations-using-gaussian","metrics":{"MSE":"4.5"},"code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-sprites","task":"Video Prediction","dataset_variant":"Sprites","rows":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper":"/paper/disentangling-representations-using-gaussian","metrics":{"MSE":"61.6"},"code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/seq2tens-an-efficient-representation-of","title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","date":"2020-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangling-representations-using-gaussian","title":"Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders","date":"2020-01-08","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}