{"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/cvthead-one-shot-controllable-head-avatar","title":"CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer","arxiv_id":"2311.06443","date":"2023-11-11","proceeding":null,"authors":["Haoyu Ma","Tong Zhang","Shanlin Sun","Xiangyi Yan","Kun Han","Xiaohui Xie"],"abstract":"Reconstructing personalized animatable head avatars has significant implications in the fields of AR/VR. Existing methods for achieving explicit face control of 3D Morphable Models (3DMM) typically rely on multi-view images or videos of a single subject, making the reconstruction process complex. Additionally, the traditional rendering pipeline is time-consuming, limiting real-time animation possibilities. In this paper, we introduce CVTHead, a novel approach that generates controllable neural head avatars from a single reference image using point-based neural rendering. CVTHead considers the sparse vertices of mesh as the point set and employs the proposed Vertex-feature Transformer to learn local feature descriptors for each vertex. This enables the modeling of long-range dependencies among all the vertices. Experimental results on the VoxCeleb dataset demonstrate that CVTHead achieves comparable performance to state-of-the-art graphics-based methods. Moreover, it enables efficient rendering of novel human heads with various expressions, head poses, and camera views. These attributes can be explicitly controlled using the coefficients of 3DMMs, facilitating versatile and realistic animation in real-time scenarios.","url_abs":"https://arxiv.org/abs/2311.06443v1","url_pdf":"https://arxiv.org/pdf/2311.06443v1.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":"cvthead-one-shot-controllable-head-avatar","repo_url":"https://github.com/howiema/cvthead","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"neural-rendering","task_name":"Neural Rendering"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.06443","atlas_url":"https://app.syntology.ai/?focus=2311.06443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06443"}},"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/howiema/cvthead","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_fixture":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"b121f7b240f2cc36","entry":"apply_imagenet_normalization","repo":"howiema/cvthead","repo_kind":"official","path":"losses/perceptual.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/losses/perceptual.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b121f7b240f2cc36"}},{"code_sha256_prefix":"1345f4fc63011f70","entry":"batched_index_select","repo":"howiema/cvthead","repo_kind":"official","path":"models/cvthead.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/models/cvthead.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1345f4fc63011f70"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"howiema/cvthead","repo_kind":"official","path":"losses/vggface.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/losses/vggface.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"325b8d54f52e2421","entry":"create_layer_basic","repo":"howiema/cvthead","repo_kind":"official","path":"models/face_parsing.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/models/face_parsing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"325b8d54f52e2421"}},{"code_sha256_prefix":"56cdde05587e0708","entry":"transform_points","repo":"howiema/cvthead","repo_kind":"official","path":"models/cvthead.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/models/cvthead.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56cdde05587e0708"}},{"code_sha256_prefix":"ddb908f010a55812","entry":"verts_to_proj_inds","repo":"howiema/cvthead","repo_kind":"official","path":"models/cvthead.py","file_url":"https://github.com/howiema/cvthead/blob/HEAD/models/cvthead.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ddb908f010a55812"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}