{"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/vitpose-vision-transformer-foundation-model","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","arxiv_id":"2212.04246","date":"2022-12-07","proceeding":null,"authors":["Yufei Xu","Jing Zhang","Qiming Zhang","DaCheng Tao"],"abstract":"In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose. Specifically, ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either a top-down or a bottom-up manner. It can be scaled up from about 20M to 1B parameters by taking advantage of the scalable model capacity and high parallelism of the vision transformer, setting a new Pareto front for throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, and pre-training and fine-tuning strategy. Based on the flexibility, a novel ViTPose+ model is proposed to deal with heterogeneous body keypoint categories in different types of body pose estimation tasks via knowledge factorization, i.e., adopting task-agnostic and task-specific feed-forward networks in the transformer. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our ViTPose model outperforms representative methods on the challenging MS COCO Human Keypoint Detection benchmark at both top-down and bottom-up settings. Furthermore, our ViTPose+ model achieves state-of-the-art performance simultaneously on a series of body pose estimation tasks, including MS COCO, AI Challenger, OCHuman, MPII for human keypoint detection, COCO-Wholebody for whole-body keypoint detection, as well as AP-10K and APT-36K for animal keypoint detection, without sacrificing inference speed.","url_abs":"https://arxiv.org/abs/2212.04246v3","url_pdf":"https://arxiv.org/pdf/2212.04246v3.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":"vitpose-vision-transformer-foundation-model","repo_url":"https://github.com/vitae-transformer/vitpose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vitpose-vision-transformer-foundation-model","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"animal-pose-estimation","task_name":"Animal Pose Estimation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"ViTPose+-H","rank_in_archive_order":8,"of":15,"metrics":{"WB":"61.2","body":"75.9","face":"63.3","foot":"77.9","hand":"54.7"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"ViTPose+-H","rank_in_archive_order":1,"of":10,"metrics":{"AP":"82.4"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"ViTPose+-L","rank_in_archive_order":2,"of":10,"metrics":{"AP":"80.4"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"ViTPose+-B","rank_in_archive_order":5,"of":10,"metrics":{"AP":"74.5"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"HRNet-w48","rank_in_archive_order":6,"of":10,"metrics":{"AP":"73.1"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"HRNet-w32","rank_in_archive_order":7,"of":10,"metrics":{"AP":"72.2"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"ViTPose+-S ViT-S","rank_in_archive_order":8,"of":10,"metrics":{"AP":"71.4"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"SimpleBaseline-ResNet50","rank_in_archive_order":9,"of":10,"metrics":{"AP":"68.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.04246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04246"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vitae-transformer/vitpose","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"24385f6e21ea88d7","entry":"get_num_layer_for_vit","repo":"vitae-transformer/vitpose","repo_kind":"official","path":"mmcv_custom/layer_decay_optimizer_constructor.py","file_url":"https://github.com/vitae-transformer/vitpose/blob/HEAD/mmcv_custom/layer_decay_optimizer_constructor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"24385f6e21ea88d7"}},{"code_sha256_prefix":"10e3dd78691455b0","entry":"covert_keypoint_definition","repo":"vitae-transformer/vitpose","repo_kind":"official","path":"demo/body3d_two_stage_video_demo.py","file_url":"https://github.com/vitae-transformer/vitpose/blob/HEAD/demo/body3d_two_stage_video_demo.py","link_basis":"harvester_set","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":"10e3dd78691455b0"}},{"code_sha256_prefix":"000768447d5adf6c","entry":"process_face_det_results","repo":"vitae-transformer/vitpose","repo_kind":"official","path":"demo/face_img_demo.py","file_url":"https://github.com/vitae-transformer/vitpose/blob/HEAD/demo/face_img_demo.py","link_basis":"harvester_set","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":"000768447d5adf6c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}