{"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/thomas-trajectory-heatmap-output-with-learned-1","title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","arxiv_id":"2110.06607","date":"2021-10-13","proceeding":"ICLR 2022 4","authors":["Thomas Gilles","Stefano Sabatini","Dzmitry Tsishkou","Bogdan Stanciulescu","Fabien Moutarde"],"abstract":"In this paper, we propose THOMAS, a joint multi-agent trajectory prediction framework allowing for an efficient and consistent prediction of multi-agent multi-modal trajectories. We present a unified model architecture for simultaneous agent future heatmap estimation, in which we leverage hierarchical and sparse image generation for fast and memory-efficient inference. We propose a learnable trajectory recombination model that takes as input a set of predicted trajectories for each agent and outputs its consistent reordered recombination. This recombination module is able to realign the initially independent modalities so that they do no collide and are coherent with each other. We report our results on the Interaction multi-agent prediction challenge and rank $1^{st}$ on the online test leaderboard.","url_abs":"https://arxiv.org/abs/2110.06607v3","url_pdf":"https://arxiv.org/pdf/2110.06607v3.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":"image-generation","task_name":"Image Generation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-forecasting-on-argoverse-cvpr-2020","task":"Motion Forecasting","dataset":"Argoverse CVPR 2020","model":"THOMAS","rank_in_archive_order":67,"of":299,"metrics":{"DAC (K=6)":"0.9781","MR (K=1)":"0.5613","MR (K=6)":"0.1038","brier-minFDE (K=6)":"1.9736","minADE (K=1)":"1.6686","minADE (K=6)":"0.9423","minFDE (K=1)":"3.593","minFDE (K=6)":"1.4388"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-prediction-on-nuscenes","task":"Trajectory Prediction","dataset":"nuScenes","model":"THOMAS","rank_in_archive_order":8,"of":34,"metrics":{"MinADE_10":"1.04","MinADE_5":"1.33","MinFDE_1":"6.71","MissRateTopK_2_10":"0.42","MissRateTopK_2_5":"0.55","OffRoadRate":"0.03"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.06607","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}