{"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/ego-body-pose-estimation-via-ego-head-pose","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","arxiv_id":"2212.04636","date":"2022-12-09","proceeding":"CVPR 2023 1","authors":["Jiaman Li","C. Karen Liu","Jiajun Wu"],"abstract":"Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. However, naively learning a mapping between egocentric videos and human motions is challenging, because the user's body is often unobserved by the front-facing camera placed on the head of the user. In addition, collecting large-scale, high-quality datasets with paired egocentric videos and 3D human motions requires accurate motion capture devices, which often limit the variety of scenes in the videos to lab-like environments. To eliminate the need for paired egocentric video and human motions, we propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. EgoEgo first integrates SLAM and a learning approach to estimate accurate head motion. Subsequently, leveraging the estimated head pose as input, EgoEgo utilizes conditional diffusion to generate multiple plausible full-body motions. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion, enabling us to leverage large-scale egocentric video datasets and motion capture datasets separately. Moreover, for systematic benchmarking, we develop a synthetic dataset, AMASS-Replica-Ego-Syn (ARES), with paired egocentric videos and human motion. On both ARES and real data, our EgoEgo model performs significantly better than the current state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2212.04636v3","url_pdf":"https://arxiv.org/pdf/2212.04636v3.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":"ego-body-pose-estimation-via-ego-head-pose","repo_url":"https://github.com/lijiaman/egoego_release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"head-pose-estimation","task_name":"Head Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2212.04636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04636"}},"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/lijiaman/egoego_release","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"unverified":12},"by_repo_kind":{"listed":{"samples":14,"ran":2,"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":"fbf9ec7be545688e","entry":"default","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/transformer_cond_diffusion_model.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_cond_diffusion_model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbf9ec7be545688e"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/transformer_cond_diffusion_model.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_cond_diffusion_model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"e8cc998064f660b5","entry":"compute_head_pose_metrics","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/eval/head_pose_metrics.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/eval/head_pose_metrics.py","link_basis":"harvester_set","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":"e8cc998064f660b5"}},{"code_sha256_prefix":"09c8479d9a5b3e06","entry":"extract","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/transformer_cond_diffusion_model.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_cond_diffusion_model.py","link_basis":"harvester_set","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":"09c8479d9a5b3e06"}},{"code_sha256_prefix":"a1ee6881f80f79fd","entry":"get_frobenious_norm","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/eval/head_pose_metrics.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/eval/head_pose_metrics.py","link_basis":"harvester_set","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":"a1ee6881f80f79fd"}},{"code_sha256_prefix":"4cd624ca825710e0","entry":"get_frobenious_norm_rot_only","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/eval/head_pose_metrics.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/eval/head_pose_metrics.py","link_basis":"harvester_set","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":"4cd624ca825710e0"}},{"code_sha256_prefix":"019b3d42e37a151d","entry":"get_heading_q_batch","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/head_estimation_transformer.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/head_estimation_transformer.py","link_basis":"harvester_set","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":"019b3d42e37a151d"}},{"code_sha256_prefix":"38165c64626f844a","entry":"get_sinusoid_encoding_table","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/transformer_module.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_module.py","link_basis":"harvester_set","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":"38165c64626f844a"}},{"code_sha256_prefix":"88956bf0120640af","entry":"get_subsequent_mask","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/transformer_module.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/transformer_module.py","link_basis":"harvester_set","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":"88956bf0120640af"}},{"code_sha256_prefix":"5a932f8b8492d39f","entry":"length","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/lafan1/utils.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/lafan1/utils.py","link_basis":"harvester_set","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":"5a932f8b8492d39f"}},{"code_sha256_prefix":"838f712f0609688a","entry":"normalize","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/lafan1/utils.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/lafan1/utils.py","link_basis":"harvester_set","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":"838f712f0609688a"}},{"code_sha256_prefix":"19c7ba2327612c9f","entry":"position_loss","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/head_estimation_transformer.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/head_estimation_transformer.py","link_basis":"harvester_set","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":"19c7ba2327612c9f"}},{"code_sha256_prefix":"e7849763e7853bec","entry":"position_loss","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/model/head_normal_estimation_transformer.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/model/head_normal_estimation_transformer.py","link_basis":"harvester_set","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":"e7849763e7853bec"}},{"code_sha256_prefix":"4e2e4e6b2574f9a6","entry":"quat_normalize","repo":"lijiaman/egoego_release","repo_kind":"listed","path":"egoego/lafan1/utils.py","file_url":"https://github.com/lijiaman/egoego_release/blob/HEAD/egoego/lafan1/utils.py","link_basis":"harvester_set","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":"4e2e4e6b2574f9a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}