{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diffmot-a-real-time-diffusion-based-multiple","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","arxiv_id":"2403.02075","date":"2024-03-04","proceeding":"CVPR 2024 1","authors":["Weiyi Lv","Yuhang Huang","Ning Zhang","Ruei-Sung Lin","Mei Han","Dan Zeng"],"abstract":"In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes. Tacking-by-detection (TBD) trackers with Kalman Filter motion prediction work well in pedestrian-dominant scenarios but fall short in complex situations when multiple objects perform non-linear and diverse motion simultaneously. To tackle the complex non-linear motion, we propose a real-time diffusion-based MOT approach named DiffMOT. Specifically, for the motion predictor component, we propose a novel Decoupled Diffusion-based Motion Predictor (D$^2$MP). It models the entire distribution of various motion presented by the data as a whole. It also predicts an individual object's motion conditioning on an individual's historical motion information. Furthermore, it optimizes the diffusion process with much fewer sampling steps. As a MOT tracker, the DiffMOT is real-time at 22.7FPS, and also outperforms the state-of-the-art on DanceTrack and SportsMOT datasets with $62.3\\%$ and $76.2\\%$ in HOTA metrics, respectively. To the best of our knowledge, DiffMOT is the first to introduce a diffusion probabilistic model into the MOT to tackle non-linear motion prediction.","url_abs":"https://arxiv.org/abs/2403.02075v2","url_pdf":"https://arxiv.org/pdf/2403.02075v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-tracking-on-quadtrack","task":"Object Tracking","dataset":"QuadTrack","model":"DiffMOT","rank_in_archive_order":7,"of":8,"metrics":{"HOTA":"16.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.02075","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}