{"url":"/task/motion-estimation","name":"Motion Estimation","slug":"motion-estimation","description_markdown":"**Motion Estimation** is used to determine the block-wise or pixel-wise motion vectors between two frames.\r\n\r\n\r\n<span class=\"description-source\">Source: [MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement ](https://arxiv.org/abs/1810.08768)</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":741,"papers_with_code":258,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":10,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/ddd17","name":"DDD17","full_name":"DAVIS Driving Dataset 2017","num_papers_in_archive":41},{"url":"/dataset/pst900","name":"PST900","full_name":null,"num_papers_in_archive":35},{"url":"/dataset/segthor","name":"SegTHOR","full_name":"Segmentation of THoracic Organs at Risk","num_papers_in_archive":28},{"url":"/dataset/ev-imo","name":"EV-IMO","full_name":"","num_papers_in_archive":22},{"url":"/dataset/fisheye-dataset","name":"Fisheye","full_name":"","num_papers_in_archive":14},{"url":"/dataset/advio","name":"ADVIO","full_name":"","num_papers_in_archive":13},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/headcam","name":"Headcam","full_name":"","num_papers_in_archive":2},{"url":"/dataset/retinal-microsurgery","name":"Retinal Microsurgery","full_name":"Retinal Microsurgery","num_papers_in_archive":2},{"url":"/dataset/x-ray-and-visible-spectra-circular-motion","name":"X-ray and Visible Spectra Circular Motion Images Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"}],"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":258,"tagged_in_all":741,"items":[{"url":"/paper/digging-into-self-supervised-monocular-depth","title":"Digging Into Self-Supervised Monocular Depth Estimation","date":"2018-06-04","arxiv_id":"1806.01260","repositories_listed":15,"syntology":{"n":24,"n_ran":17,"n_unverified":7,"n_pointer_only":6}},{"url":"/paper/depth-prediction-without-the-sensors","title":"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","date":"2018-11-15","arxiv_id":"1811.06152","repositories_listed":11,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/the-double-sphere-camera-model","title":"The Double Sphere Camera Model","date":"2018-07-24","arxiv_id":"1807.08957","repositories_listed":9,"syntology":null},{"url":"/paper/on-human-motion-prediction-using-recurrent","title":"On human motion prediction using recurrent neural networks","date":"2017-05-06","arxiv_id":"1705.02445","repositories_listed":8,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/visual-inertial-mapping-with-non-linear","title":"Visual-Inertial Mapping with Non-Linear Factor Recovery","date":"2019-04-13","arxiv_id":"1904.06504","repositories_listed":7,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/scalable-scene-flow-from-point-clouds-in-the","title":"Scalable Scene Flow from Point Clouds in the Real World","date":"2021-03-01","arxiv_id":"2103.01306","repositories_listed":5,"syntology":null},{"url":"/paper/fastdvdnet-towards-real-time-video-denoising","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","date":"2019-07-01","arxiv_id":"1907.01361","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deepvo-towards-end-to-end-visual-odometry","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","date":"2017-09-25","arxiv_id":"1709.08429","repositories_listed":5,"syntology":null},{"url":"/paper/castle-in-the-sky-dynamic-sky-replacement-and","title":"Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos","date":"2020-10-22","arxiv_id":"2010.11800","repositories_listed":4,"syntology":null},{"url":"/paper/sme-net-sparse-motion-estimation-for","title":"SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning","date":"2019-10-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/deepphys-video-based-physiological","title":"DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks","date":"2018-05-21","arxiv_id":"1805.07888","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/video-enhancement-with-task-oriented-flow","title":"Video Enhancement with Task-Oriented Flow","date":"2017-11-24","arxiv_id":"1711.09078","repositories_listed":4,"syntology":null},{"url":"/paper/tapir-tracking-any-point-with-per-frame","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","date":"2023-06-14","arxiv_id":"2306.08637","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/micro-expression-generation-with-thin-plate","title":"Micro Expression Generation with Thin-plate Spline Motion Model and Face Parsing","date":"2022-10-10","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/exploring-simple-3d-multi-object-tracking-for","title":"Exploring Simple 3D Multi-Object Tracking for Autonomous Driving","date":"2021-08-23","arxiv_id":"2108.10312","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/stereo-relative-pose-from-line-and-point-1","title":"Stereo relative pose from line and point feature triplets","date":"2019-06-29","arxiv_id":"1907.00276","repositories_listed":3,"syntology":null},{"url":"/paper/weakly-supervised-deep-recurrent-neural","title":"Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation","date":"2018-07-03","arxiv_id":"1807.01126","repositories_listed":3,"syntology":null},{"url":"/paper/geonet-unsupervised-learning-of-dense-depth","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","date":"2018-03-06","arxiv_id":"1803.02276","repositories_listed":3,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/hp-gan-probabilistic-3d-human-motion","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","date":"2017-11-27","arxiv_id":"1711.09561","repositories_listed":3,"syntology":null},{"url":"/paper/oflib-facilitating-operations-with-and-on","title":"Oflib: Facilitating Operations with and on Optical Flow Fields in Python","date":"2022-10-11","arxiv_id":"2210.05635","repositories_listed":2,"syntology":null},{"url":"/paper/visual-pursuit-control-based-on-gaussian","title":"Visual Pursuit Control based on Gaussian Processes with Switched Motion Trajectories","date":"2022-08-18","arxiv_id":"2208.08645","repositories_listed":2,"syntology":null},{"url":"/paper/flexible-rate-learned-hierarchical-bi","title":"Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit Allocation","date":"2022-06-27","arxiv_id":"2206.13613","repositories_listed":2,"syntology":null},{"url":"/paper/realnet-combining-optimized-object-detection","title":"RealNet: Combining Optimized Object Detection with Information Fusion Depth Estimation Co-Design Method on IoT","date":"2022-04-24","arxiv_id":"2204.11216","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-rate-distortion-optimized-learned","title":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","date":"2021-12-17","arxiv_id":"2112.09529","repositories_listed":2,"syntology":null},{"url":"/paper/deep-homography-estimation-in-dynamic","title":"Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction","date":"2021-09-30","arxiv_id":"2109.15098","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-landmark-detection-based","title":"Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images","date":"2021-09-30","arxiv_id":"2109.14805","repositories_listed":2,"syntology":null},{"url":"/paper/recurrent-video-deblurring-with-blur","title":"Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes","date":"2021-08-23","arxiv_id":"2108.09982","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/spatiotemporal-registration-for-event-based","title":"Spatiotemporal Registration for Event-based Visual Odometry","date":"2021-03-10","arxiv_id":"2103.05955","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-depth-and-ego-motion-estimation","title":"Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss","date":"2021-03-01","arxiv_id":"2103.00760","repositories_listed":2,"syntology":null},{"url":"/paper/cnn-based-visual-ego-motion-estimation-for","title":"CNN-based Ego-Motion Estimation for Fast MAV Maneuvers","date":"2021-01-06","arxiv_id":"2101.01841","repositories_listed":2,"syntology":null}],"syntology_records":10,"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"}}