{"url":"/task/video-reconstruction","name":"Video Reconstruction","slug":"video-reconstruction","description_markdown":"<span class=\"description-source\">Source: [Deep-SloMo](https://github.com/avinashpaliwal/Deep-SloMo)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":145,"papers_with_code":55,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-reconstruction-on-uvg","slug":"video-reconstruction-on-uvg","dataset":"UVG","dataset_url":null,"rows_in_archive":7,"metrics":["Average PSNR (dB)","Model Size (M)"],"first_row_in_archive_order":{"model":"HiNeRV","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-reconstruction-on-event-camera-dataset","slug":"video-reconstruction-on-event-camera-dataset","dataset":"Event-Camera Dataset","dataset_url":"/dataset/event-camera-dataset","rows_in_archive":4,"metrics":["Mean Squared Error","LPIPS"],"first_row_in_archive_order":{"model":"HyperE2VID","paper_title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","paper_url":"/paper/hypere2vid-improving-event-based-video","paper_date":"2023-05-10","arxiv_id":"2305.06382","code_links":[{"title":"ercanburak/HyperE2VID","url":"https://github.com/ercanburak/HyperE2VID"}],"syntology":null}},{"leaderboard":"/sota/video-reconstruction-on-mvsec","slug":"video-reconstruction-on-mvsec","dataset":"MVSEC","dataset_url":"/dataset/mvsec","rows_in_archive":4,"metrics":["Mean Squared Error","LPIPS"],"first_row_in_archive_order":{"model":"HyperE2VID","paper_title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","paper_url":"/paper/hypere2vid-improving-event-based-video","paper_date":"2023-05-10","arxiv_id":"2305.06382","code_links":[{"title":"ercanburak/HyperE2VID","url":"https://github.com/ercanburak/HyperE2VID"}],"syntology":null}},{"leaderboard":"/sota/video-reconstruction-on-mgif","slug":"video-reconstruction-on-mgif","dataset":"MGif","dataset_url":"/dataset/mgif","rows_in_archive":2,"metrics":["L1"],"first_row_in_archive_order":{"model":"Siarohin et al.","paper_title":"Motion Representations for Articulated Animation","paper_url":"/paper/motion-representations-for-articulated-1","paper_date":"2021-04-22","arxiv_id":"2104.11280","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"snap-research/articulated-animation","url":"https://github.com/snap-research/articulated-animation"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/video-reconstruction-on-tai-chi-hd-256","slug":"video-reconstruction-on-tai-chi-hd-256","dataset":"Tai-Chi-HD (256)","dataset_url":"/dataset/tai-chi-hd","rows_in_archive":2,"metrics":["AED","AKD","L1","MKR"],"first_row_in_archive_order":{"model":"Siarohin et al.","paper_title":"Motion Representations for Articulated Animation","paper_url":"/paper/motion-representations-for-articulated-1","paper_date":"2021-04-22","arxiv_id":"2104.11280","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"snap-research/articulated-animation","url":"https://github.com/snap-research/articulated-animation"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/video-reconstruction-on-tai-chi-hd-512","slug":"video-reconstruction-on-tai-chi-hd-512","dataset":"Tai-Chi-HD (512)","dataset_url":"/dataset/tai-chi-hd","rows_in_archive":2,"metrics":["AED","AKD","L1","MKR"],"first_row_in_archive_order":{"model":"Siarohin et al.","paper_title":"Motion Representations for Articulated Animation","paper_url":"/paper/motion-representations-for-articulated-1","paper_date":"2021-04-22","arxiv_id":"2104.11280","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"snap-research/articulated-animation","url":"https://github.com/snap-research/articulated-animation"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/video-reconstruction-on-ted-talks","slug":"video-reconstruction-on-ted-talks","dataset":"TED-talks","dataset_url":"/dataset/ted-talks","rows_in_archive":2,"metrics":["AED","AKD","L1","MKR"],"first_row_in_archive_order":{"model":"Siarohin et al.","paper_title":"Motion Representations for Articulated Animation","paper_url":"/paper/motion-representations-for-articulated-1","paper_date":"2021-04-22","arxiv_id":"2104.11280","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"snap-research/articulated-animation","url":"https://github.com/snap-research/articulated-animation"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/video-reconstruction-on-voxceleb","slug":"video-reconstruction-on-voxceleb","dataset":"VoxCeleb","dataset_url":"/dataset/voxceleb1","rows_in_archive":2,"metrics":["AED","AKD","L1"],"first_row_in_archive_order":{"model":"Siarohin et al.","paper_title":"Motion Representations for Articulated Animation","paper_url":"/paper/motion-representations-for-articulated-1","paper_date":"2021-04-22","arxiv_id":"2104.11280","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"snap-research/articulated-animation","url":"https://github.com/snap-research/articulated-animation"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}}},{"leaderboard":"/sota/video-reconstruction-on-tai-chi-hd","slug":"video-reconstruction-on-tai-chi-hd","dataset":"Tai-Chi-HD","dataset_url":"/dataset/tai-chi-hd","rows_in_archive":1,"metrics":["L1"],"first_row_in_archive_order":{"model":"First Order Motion","paper_title":"First Order Motion Model for Image Animation","paper_url":"/paper/first-order-motion-model-for-image-animation-1","paper_date":"2020-02-29","arxiv_id":"2003.00196","code_links":[{"title":"AliaksandrSiarohin/first-order-model","url":"https://github.com/AliaksandrSiarohin/first-order-model"},{"title":"xih108/Video_Completion","url":"https://github.com/xih108/Video_Completion"},{"title":"abhaskumarsinha/KMT","url":"https://github.com/abhaskumarsinha/KMT"}],"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/event-camera-dataset","name":"Event-Camera Dataset","full_name":"","num_papers_in_archive":51},{"url":"/dataset/mvsec","name":"MVSEC","full_name":"Multi Vehicle Stereo Event Camera","num_papers_in_archive":28},{"url":"/dataset/mgif","name":"MGif","full_name":"","num_papers_in_archive":14},{"url":"/dataset/ted-talks","name":"TED-talks","full_name":"","num_papers_in_archive":13},{"url":"/dataset/tai-chi-hd","name":"Tai-Chi-HD","full_name":"","num_papers_in_archive":9},{"url":"/dataset/sen12ms-cr-ts","name":"SEN12MS-CR-TS","full_name":"SEN12MS-CR-TS","num_papers_in_archive":7},{"url":"/dataset/i2-2000fps","name":"I2-2000FPS","full_name":"","num_papers_in_archive":2},{"url":"/dataset/videezy4k","name":"Videezy4K","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/3d","name":"3D"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":55,"tagged_in_all":145,"items":[{"url":"/paper/videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","repositories_listed":9,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":12}},{"url":"/paper/step-video-t2v-technical-report-the-practice","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","date":"2025-02-14","arxiv_id":"2502.10248","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/nerv-neural-representations-for-videos","title":"NeRV: Neural Representations for Videos","date":"2021-10-26","arxiv_id":"2110.13903","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/first-order-motion-model-for-image-animation-1","title":"First Order Motion Model for Image Animation","date":"2020-02-29","arxiv_id":"2003.00196","repositories_listed":3,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/image-and-video-tokenization-with-binary","title":"Image and Video Tokenization with Binary Spherical Quantization","date":"2024-06-11","arxiv_id":"2406.07548","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/joint-video-multi-frame-interpolation-and","title":"Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time","date":"2023-03-27","arxiv_id":"2303.15043","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/layered-neural-atlases-for-consistent-video","title":"Layered Neural Atlases for Consistent Video Editing","date":"2021-09-23","arxiv_id":"2109.11418","repositories_listed":2,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/motion-representations-for-articulated-1","title":"Motion Representations for Articulated Animation","date":"2021-04-22","arxiv_id":"2104.11280","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}},{"url":"/paper/v2v-scaling-event-based-vision-through","title":"V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation","date":"2025-05-22","arxiv_id":"2505.16797","repositories_listed":1,"syntology":null},{"url":"/paper/learning-adaptive-and-temporally-causal-video","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space","date":"2025-05-22","arxiv_id":"2505.17011","repositories_listed":1,"syntology":null},{"url":"/paper/leanvae-an-ultra-efficient-reconstruction-vae","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","date":"2025-03-18","arxiv_id":"2503.14325","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/neurons-emulating-the-human-visual-cortex","title":"Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction","date":"2025-03-14","arxiv_id":"2503.11167","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/rethinking-video-tokenization-a-conditioned","title":"Rethinking Video Tokenization: A Conditioned Diffusion-based Approach","date":"2025-03-05","arxiv_id":"2503.03708","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-world-dynamics-in-a-nutshell","title":"Seeing World Dynamics in a Nutshell","date":"2025-02-05","arxiv_id":"2502.03465","repositories_listed":1,"syntology":null},{"url":"/paper/vision-xl-high-definition-video-inverse","title":"VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models","date":"2024-11-29","arxiv_id":"2412.00156","repositories_listed":1,"syntology":null},{"url":"/paper/bit2bit-1-bit-quanta-video-reconstruction-via","title":"bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction","date":"2024-10-30","arxiv_id":"2410.23247","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","arxiv_id":"2410.21264","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/neuroclips-towards-high-fidelity-and-smooth","title":"NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction","date":"2024-10-25","arxiv_id":"2410.19452","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/od-vae-an-omni-dimensional-video-compressor","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model","date":"2024-09-02","arxiv_id":"2409.01199","repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-temporal-updating-network-for","title":"Cascaded Temporal Updating Network for Efficient Video Super-Resolution","date":"2024-08-26","arxiv_id":"2408.14244","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-low-bit-quantization-framework-for","title":"A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging","date":"2024-07-31","arxiv_id":"2407.21517","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-event-stream-super-resolution-with","title":"Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion","date":"2024-06-28","arxiv_id":"2406.19640","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/bilateral-event-mining-and-complementary-for","title":"Bilateral Event Mining and Complementary for Event Stream Super-Resolution","date":"2024-05-16","arxiv_id":"2405.10037","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/towards-real-world-hdr-video-reconstruction-a","title":"Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network","date":"2024-04-30","arxiv_id":"2405.00244","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-feedback-discriminative","title":"Collaborative Feedback Discriminative Propagation for Video Super-Resolution","date":"2024-04-06","arxiv_id":"2404.04745","repositories_listed":1,"syntology":null},{"url":"/paper/towards-4d-human-video-stylization","title":"Towards 4D Human Video Stylization","date":"2023-12-07","arxiv_id":"2312.04143","repositories_listed":1,"syntology":null},{"url":"/paper/an-asynchronous-linear-filter-architecture","title":"An Asynchronous Linear Filter Architecture for Hybrid Event-Frame Cameras","date":"2023-09-03","arxiv_id":"2309.01159","repositories_listed":1,"syntology":null},{"url":"/paper/lan-hdr-luminance-based-alignment-network-for","title":"LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction","date":"2023-08-22","arxiv_id":"2308.11116","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_unverified":6,"n_pointer_only":18}},{"url":"/paper/sensing-diversity-and-sparsity-models-for","title":"Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events","date":"2023-05-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hypere2vid-improving-event-based-video","title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","date":"2023-05-10","arxiv_id":"2305.06382","repositories_listed":1,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}