{"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/echomimicv2-towards-striking-simplified-and","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","arxiv_id":"2411.10061","date":"2024-11-15","proceeding":"CVPR 2025 1","authors":["Rang Meng","Xingyu Zhang","Yuming Li","Chenguang Ma"],"abstract":"Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality. However, these methods often face practical challenges due to extra control conditions, cumbersome condition injection modules, or limitation to head region driving. Hence, we ask if it is possible to achieve striking half-body human animation while simplifying unnecessary conditions. To this end, we propose a half-body human animation method, dubbed EchoMimicV2, that leverages a novel Audio-Pose Dynamic Harmonization strategy, including Pose Sampling and Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize Head Partial Attention to seamlessly accommodate headshot data into our training framework, which can be omitted during inference, providing a free lunch for animation. Furthermore, we design the Phase-specific Denoising Loss to guide motion, detail, and low-level quality for animation in specific phases, respectively. Besides, we also present a novel benchmark for evaluating the effectiveness of half-body human animation. Extensive experiments and analyses demonstrate that EchoMimicV2 surpasses existing methods in both quantitative and qualitative evaluations.","url_abs":"https://arxiv.org/abs/2411.10061v1","url_pdf":"https://arxiv.org/pdf/2411.10061v1.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":"echomimicv2-towards-striking-simplified-and","repo_url":"https://github.com/antgroup/echomimic_v2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-driven-body-animation","task_name":"Audio-Driven Body Animation"},{"task_slug":"human-animation","task_name":"Human Animation"},{"task_slug":"image-to-video","task_name":"Image to Video Generation"},{"task_slug":"subject-driven-video-generation","task_name":"Subject-driven Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.10061","atlas_url":"https://app.syntology.ai/?focus=2411.10061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10061"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/antgroup/echomimic_v2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"4719c763c53be3fe","entry":"zero_module","repo":"antgroup/echomimic_v2","repo_kind":"official","path":"src/models/motion_module.py","file_url":"https://github.com/antgroup/echomimic_v2/blob/HEAD/src/models/motion_module.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4719c763c53be3fe"}},{"code_sha256_prefix":"525d02f457ec7c07","entry":"get_motion_module","repo":"antgroup/echomimic_v2","repo_kind":"official","path":"src/models/motion_module.py","file_url":"https://github.com/antgroup/echomimic_v2/blob/HEAD/src/models/motion_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"525d02f457ec7c07"}},{"code_sha256_prefix":"0011e6b34a38a1f2","entry":"resize_and_pad","repo":"antgroup/echomimic_v2","repo_kind":"official","path":"EMTD_dataset/preprocess.py","file_url":"https://github.com/antgroup/echomimic_v2/blob/HEAD/EMTD_dataset/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0011e6b34a38a1f2"}},{"code_sha256_prefix":"4118b8d2b95fe19f","entry":"resize_and_pad_param","repo":"antgroup/echomimic_v2","repo_kind":"official","path":"EMTD_dataset/preprocess.py","file_url":"https://github.com/antgroup/echomimic_v2/blob/HEAD/EMTD_dataset/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4118b8d2b95fe19f"}},{"code_sha256_prefix":"e55f24470648724c","entry":"torch_dfs","repo":"antgroup/echomimic_v2","repo_kind":"official","path":"src/models/mutual_self_attention.py","file_url":"https://github.com/antgroup/echomimic_v2/blob/HEAD/src/models/mutual_self_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e55f24470648724c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}