{"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/champ-controllable-and-consistent-human-image","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","arxiv_id":"2403.14781","date":"2024-03-21","proceeding":null,"authors":["Shenhao Zhu","Junming Leo Chen","Zuozhuo Dai","Qingkun Su","Yinghui Xu","Xun Cao","Yao Yao","Hao Zhu","Siyu Zhu"],"abstract":"In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques. The methodology utilizes the SMPL(Skinned Multi-Person Linear) model as the 3D human parametric model to establish a unified representation of body shape and pose. This facilitates the accurate capture of intricate human geometry and motion characteristics from source videos. Specifically, we incorporate rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, alongside skeleton-based motion guidance, to enrich the conditions to the latent diffusion model with comprehensive 3D shape and detailed pose attributes. A multi-layer motion fusion module, integrating self-attention mechanisms, is employed to fuse the shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion. Experimental evaluations conducted on benchmark datasets demonstrate the methodology's superior ability to generate high-quality human animations that accurately capture both pose and shape variations. Furthermore, our approach also exhibits superior generalization capabilities on the proposed in-the-wild dataset. Project page: https://fudan-generative-vision.github.io/champ.","url_abs":"https://arxiv.org/abs/2403.14781v2","url_pdf":"https://arxiv.org/pdf/2403.14781v2.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":"champ-controllable-and-consistent-human-image","repo_url":"https://github.com/fudan-generative-vision/champ","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"animated-gif-generation","task_name":"Animated GIF Generation"},{"task_slug":"image-animation","task_name":"Image Animation"},{"task_slug":"image-to-video","task_name":"Image to Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.14781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14781"}},"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/fudan-generative-vision/champ","reach":{"status":"ok","spdx":"MIT"}}],"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":"fudan-generative-vision/champ","repo_kind":"official","path":"models/motion_module.py","file_url":"https://github.com/fudan-generative-vision/champ/blob/HEAD/models/motion_module.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4719c763c53be3fe"}},{"code_sha256_prefix":"525d02f457ec7c07","entry":"get_motion_module","repo":"fudan-generative-vision/champ","repo_kind":"official","path":"models/motion_module.py","file_url":"https://github.com/fudan-generative-vision/champ/blob/HEAD/models/motion_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":"525d02f457ec7c07"}},{"code_sha256_prefix":"4cd67a96b274d180","entry":"process_semantic_map","repo":"fudan-generative-vision/champ","repo_kind":"official","path":"inference.py","file_url":"https://github.com/fudan-generative-vision/champ/blob/HEAD/inference.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":"4cd67a96b274d180"}},{"code_sha256_prefix":"fb6eb3e0108d92db","entry":"setup_savedir","repo":"fudan-generative-vision/champ","repo_kind":"official","path":"inference.py","file_url":"https://github.com/fudan-generative-vision/champ/blob/HEAD/inference.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":"fb6eb3e0108d92db"}},{"code_sha256_prefix":"e55f24470648724c","entry":"torch_dfs","repo":"fudan-generative-vision/champ","repo_kind":"official","path":"models/mutual_self_attention.py","file_url":"https://github.com/fudan-generative-vision/champ/blob/HEAD/models/mutual_self_attention.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":"e55f24470648724c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}