{"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/eqmotion-equivariant-multi-agent-motion","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","arxiv_id":"2303.10876","date":"2023-03-20","proceeding":"CVPR 2023 1","authors":["Chenxin Xu","Robby T. Tan","Yuhong Tan","Siheng Chen","Yu Guang Wang","Xinchao Wang","Yanfeng Wang"],"abstract":"Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle. However, such equivariance and invariance properties are overlooked by most existing methods. To fill this gap, we propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. To achieve motion equivariance, we propose an equivariant geometric feature learning module to learn a Euclidean transformable feature through dedicated designs of equivariant operations. To reason agent's interactions, we propose an invariant interaction reasoning module to achieve a more stable interaction modeling. To further promote more comprehensive motion features, we propose an invariant pattern feature learning module to learn an invariant pattern feature, which cooperates with the equivariant geometric feature to enhance network expressiveness. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Experimental results show that our method is not only generally applicable, but also achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%. Code is available at https://github.com/MediaBrain-SJTU/EqMotion.","url_abs":"https://arxiv.org/abs/2303.10876v2","url_pdf":"https://arxiv.org/pdf/2303.10876v2.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":[{"paper_slug":"eqmotion-equivariant-multi-agent-motion","repo_url":"https://github.com/mediabrain-sjtu/eqmotion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eqmotion-equivariant-multi-agent-motion","repo_url":"https://github.com/pranav-chib/trajimpute","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"human-pose-forecasting","task_name":"Human Pose Forecasting"},{"task_slug":"pedestrian-trajectory-prediction","task_name":"Pedestrian Trajectory Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-pose-forecasting-on-harper","task":"Human Pose Forecasting","dataset":"HARPER","model":"EqMotion","rank_in_archive_order":1,"of":3,"metrics":{"Average MPJPE (mm) @ 1000ms":"104","Average MPJPE (mm) @ 400ms":"41","Last Frame MPJPE (mm) @ 1000ms":"197","Last Frame MPJPE (mm) @ 400ms":"69"},"uses_additional_data":false},{"leaderboard":"/sota/human-pose-forecasting-on-human36m","task":"Human Pose Forecasting","dataset":"Human3.6M","model":"EqMotion","rank_in_archive_order":5,"of":33,"metrics":{"Average MPJPE (mm) @ 1000 ms":"106.9","Average MPJPE (mm) @ 400ms":"55.0"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-prediction-on-ethucy","task":"Trajectory Prediction","dataset":"ETH/UCY","model":"EqMotion","rank_in_archive_order":9,"of":20,"metrics":{"ADE-8/12":"0.21"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.10876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10876"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pranav-chib/trajimpute","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mediabrain-sjtu/eqmotion","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MediaBrain-SJTU/EqMotion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fd51b78759687dd9","entry":"Feature_learning_layer","repo":"MediaBrain-SJTU/EqMotion","repo_kind":"official","path":"eth_ucy/model_t.py","file_url":"https://github.com/MediaBrain-SJTU/EqMotion/blob/HEAD/eth_ucy/model_t.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd51b78759687dd9"}},{"code_sha256_prefix":"d913b3a19d46ce7e","entry":"EqMotion","repo":"MediaBrain-SJTU/EqMotion","repo_kind":"official","path":"eth_ucy/model_t.py","file_url":"https://github.com/MediaBrain-SJTU/EqMotion/blob/HEAD/eth_ucy/model_t.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d913b3a19d46ce7e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}