{"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/predicting-3d-human-dynamics-from-video","title":"Predicting 3D Human Dynamics from Video","arxiv_id":"1908.04781","date":"2019-08-13","proceeding":"ICCV 2019 10","authors":["Jason Y. Zhang","Panna Felsen","Angjoo Kanazawa","Jitendra Malik"],"abstract":"Given a video of a person in action, we can easily guess the 3D future motion of the person. In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input. We do this for periodic motions such as walking and also actions like bowling and squatting seen in sports or workout videos. While there has been a surge of future prediction problems in computer vision, most approaches predict 3D future from 3D past or 2D future from 2D past inputs. In this work, we focus on the problem of predicting 3D future motion from past image sequences, which has a plethora of practical applications in autonomous systems that must operate safely around people from visual inputs. Inspired by the success of autoregressive models in language modeling tasks, we learn an intermediate latent space on which we predict the future. This effectively facilitates autoregressive predictions when the input differs from the output domain. Our approach can be trained on video sequences obtained in-the-wild without 3D ground truth labels. The project website with videos can be found at https://jasonyzhang.com/phd.","url_abs":"https://arxiv.org/abs/1908.04781v2","url_pdf":"https://arxiv.org/pdf/1908.04781v2.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":"predicting-3d-human-dynamics-from-video","repo_url":"https://github.com/jasonyzhang/phd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"3d-human-dynamics","task_name":"3D Human Dynamics"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"future-prediction","task_name":"Future prediction"},{"task_slug":"human-dynamics","task_name":"Human Dynamics"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.04781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04781"}},"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/jasonyzhang/phd","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":17},"by_repo_kind":{"official":{"samples":17,"ran":0,"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":"74c9b49c72a62f9d","entry":"batch_orth_proj_idrot","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/projection.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/projection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"74c9b49c72a62f9d"}},{"code_sha256_prefix":"c7079337574a09d2","entry":"batch_orth_proj_optcam","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/projection.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/projection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c7079337574a09d2"}},{"code_sha256_prefix":"785c66706574bea1","entry":"batch_rodrigues","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/batch_lbs.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/batch_lbs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"785c66706574bea1"}},{"code_sha256_prefix":"5b19861e6645f0be","entry":"batch_rot2aa","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/batch_lbs.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/batch_lbs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5b19861e6645f0be"}},{"code_sha256_prefix":"fca9ceed95411f50","entry":"batch_skew","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/batch_lbs.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/batch_lbs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fca9ceed95411f50"}},{"code_sha256_prefix":"b29fcb58b1cffa5f","entry":"compute_tracks","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/extract_tracks.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/extract_tracks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b29fcb58b1cffa5f"}},{"code_sha256_prefix":"695ee32917b465d7","entry":"get_dims","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/renderer.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/renderer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"695ee32917b465d7"}},{"code_sha256_prefix":"3a63d35b434d3196","entry":"get_labels_poseflow","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/extract_tracks.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/extract_tracks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3a63d35b434d3196"}},{"code_sha256_prefix":"59c1352c7c8f0c7b","entry":"get_output_path_name","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/evaluation/run_video.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/evaluation/run_video.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"59c1352c7c8f0c7b"}},{"code_sha256_prefix":"2cde9da4227a4934","entry":"process_videos","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/evaluation/run_video.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/evaluation/run_video.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2cde9da4227a4934"}},{"code_sha256_prefix":"8a9b610b726cca33","entry":"procrustes2d_vis","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/projection.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/projection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8a9b610b726cca33"}},{"code_sha256_prefix":"ab7d47670a4b49ba","entry":"resize_img","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/util/common.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/util/common.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ab7d47670a4b49ba"}},{"code_sha256_prefix":"0b220a0d1abc1008","entry":"run_poseflow","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/extract_tracks.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/extract_tracks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0b220a0d1abc1008"}},{"code_sha256_prefix":"05191822268f47e6","entry":"tf_pad","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/ops.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"05191822268f47e6"}},{"code_sha256_prefix":"e5f55a88efd3909d","entry":"to_float_tensor","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/renderer.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/renderer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e5f55a88efd3909d"}},{"code_sha256_prefix":"2e0b2d1dc17197f6","entry":"to_variable","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/renderer.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/renderer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2e0b2d1dc17197f6"}},{"code_sha256_prefix":"e24744b154d5aa09","entry":"undo_chumpy","repo":"jasonyzhang/phd","repo_kind":"official","path":"src/tf_smpl/batch_smpl.py","file_url":"https://github.com/jasonyzhang/phd/blob/HEAD/src/tf_smpl/batch_smpl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e24744b154d5aa09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}