{"url":"/method/motionnet","slug":"motionnet","name":"MotionNet","full_name":"MotionNet","full_name_withheld":false,"description_markdown":"**MotionNet** is a system for joint perception and motion prediction based on a bird's eye view (BEV) map, which encodes the object category and motion information from 3D point clouds in each grid cell. MotionNet takes a sequence of LiDAR sweeps as input and outputs the bird's eye view (BEV) map. The backbone of MotionNet is a spatio-temporal pyramid network, which extracts deep spatial and temporal features in a hierarchical fashion. To enforce the smoothness of predictions over both space and time, the training of MotionNet is further regularized with novel spatial and temporal consistency losses.","description_state":"present","introduced_year":null,"introduced_by":{"title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","paper":"/paper/motionnet-joint-perception-and-motion","first_author":"Pengxiang Wu","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/motionnet-joint-perception-and-motion"},"source":{"url":"https://arxiv.org/abs/2003.06754v1","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Motion Prediction Models","url":"/methods/category/motion-prediction-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":null,"title":"Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes","date":"2020-11-18","arxiv_id":"2011.09369","n_code_links":0,"syntology":null},{"paper":"/paper/motionnet-joint-perception-and-motion","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","date":"2020-03-15","arxiv_id":"2003.06754","n_code_links":2,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/motion-prediction","name":"motion prediction","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2020","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/motionnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}