{"url":"/dataset/spike-x4k","name":"Spike-X4K","full_name":"Spike-X4K Dataset","description_markdown":"## Overview\r\nThe Spike-X4K Dataset is a high-resolution image reconstruction resource tailored for the latest advancements in spike camera technology. It is designed to meet the demands of modern spike cameras with a resolution of 1000×1000 pixels, surpassing the capabilities of previous datasets like spike-REDS, which was limited to a resolution of 250×400 pixels.\r\n\r\n## Dataset Characteristics\r\n- **Resolution**: 1000×1000 pixels, aligning with state-of-the-art spike camera imaging standards.\r\n- **Temporal Depth**: The dataset captures the temporal dynamics of scenes with high-speed motion, providing a temporal sequence of spike frames.\r\n- **Content**: It includes both synthetic and real-world datasets, offering a diverse range of high-speed motion scenarios for training and testing image reconstruction models.\r\n- **Pairs**: The dataset comprises 1200 spike stream-ground truth image pairs for training and 45 pairs for testing, ensuring robust model evaluation.\r\n\r\n## Motivation and Content Summary\r\nThe development of the Spike-X4K Dataset was motivated by the need for a more representative and higher resolution dataset that could effectively train and evaluate image reconstruction models for spike cameras. Spike cameras, with their unique ability to capture photons independently at each pixel and generate binary spike streams, offer high temporal resolution and low latency, which are crucial for high-speed imaging. However, converting these spike streams into high-quality images requires sophisticated algorithms, and the Spike-X4K Dataset provides the necessary data to develop and refine these algorithms.\r\n\r\n## Potential Use Cases\r\n1. **Algorithm Development**: For researchers and engineers working on spike image reconstruction algorithms specific to spike camera data.\r\n2. **Benchmarking**: As a standard for benchmarking the performance of various image reconstruction models against state-of-the-art techniques.\r\n3. **Training and Testing**: Providing a large and diverse set of data for training deep learning models to handle high-speed motion imaging.\r\n4. **Feature Extraction**: Enabling the study and improvement of feature extraction techniques from spike streams, including spatial and temporal features.\r\n5. **Spike Image Reconstruction Tasks**: Supporting a wide range of computer vision tasks that can benefit from high-resolution, high-speed imaging, such as motion analysis, object tracking, and event detection.","description_withheld":null,"homepage":"https://github.com/bupt-ai-cz/SwinSF","introduced_date":"2024-07-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/swinsf-image-reconstruction-from-spatial","title":"SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams","first_author":"Liangyan Jiang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Image Reconstruction","url":"/task/image-reconstruction","datasets_with_task":"/datasets/task/image-reconstruction"},{"name":"Event-based vision","url":"/task/event-based-vision","datasets_with_task":"/datasets/task/event-based-vision"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Spike-X4K"],"data_loaders":[{"repo":"https://github.com/bupt-ai-cz/SwinSF","url":"https://github.com/bupt-ai-cz/SwinSF","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-reconstruction-on-spike-x4k","task":"Image Reconstruction","dataset_variant":"Spike-X4K","rows":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"SwinSF","paper":"/paper/swinsf-image-reconstruction-from-spatial","metrics":{"Average PSNR":"39.61"},"code_links":[{"title":"bupt-ai-cz/SwinSF","url":"https://github.com/bupt-ai-cz/SwinSF"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/swinsf-image-reconstruction-from-spatial","title":"SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}