{"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/rethink-sparse-signals-for-pose-guided-text","title":"Rethink Sparse Signals for Pose-guided Text-to-image Generation","arxiv_id":"2506.20983","date":"2025-06-26","proceeding":null,"authors":["Wenjie Xuan","Jing Zhang","Juhua Liu","Bo Du","DaCheng Tao"],"abstract":"Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-image generation. However, dense representations raised new challenges, including editing difficulties and potential inconsistencies with textual prompts. This fact motivates us to revisit sparse signals for pose guidance, owing to their simplicity and shape-agnostic nature, which remains underexplored. This paper proposes a novel Spatial-Pose ControlNet(SP-Ctrl), equipping sparse signals with robust controllability for pose-guided image generation. Specifically, we extend OpenPose to a learnable spatial representation, making keypoint embeddings discriminative and expressive. Additionally, we introduce keypoint concept learning, which encourages keypoint tokens to attend to the spatial positions of each keypoint, thus improving pose alignment. Experiments on animal- and human-centric image generation tasks demonstrate that our method outperforms recent spatially controllable T2I generation approaches under sparse-pose guidance and even matches the performance of dense signal-based methods. Moreover, SP-Ctrl shows promising capabilities in diverse and cross-species generation through sparse signals. Codes will be available at https://github.com/DREAMXFAR/SP-Ctrl.","url_abs":"https://arxiv.org/abs/2506.20983v1","url_pdf":"https://arxiv.org/pdf/2506.20983v1.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":"rethink-sparse-signals-for-pose-guided-text","repo_url":"https://github.com/dreamxfar/sp-ctrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"pose-guided-image-generation","task_name":"Pose-Guided Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"openpose","method_name":"OpenPose"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.20983","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}