{"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/signing-at-scale-learning-to-co-articulate","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","arxiv_id":"2203.15354","date":"2022-03-29","proceeding":"CVPR 2022 1","authors":["Ben Saunders","Necati Cihan Camgoz","Richard Bowden"],"abstract":"Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from constrained vocabularies and this limits applicability. To be understandable and accepted by the deaf, an automatic SLP system must be able to generate co-articulated photo-realistic signing sequences for large domains of discourse. In this work, we tackle large-scale SLP by learning to co-articulate between dictionary signs, a method capable of producing smooth signing while scaling to unconstrained domains of discourse. To learn sign co-articulation, we propose a novel Frame Selection Network (FS-Net) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences. Additionally, we propose SignGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose. We propose a novel keypoint-based loss function which improves the quality of synthesized hand images. We evaluate our SLP model on the large-scale meineDGS (mDGS) corpus, conducting extensive user evaluation showing our FS-Net approach improves co-articulation of interpolated dictionary signs. Additionally, we show that SignGAN significantly outperforms all baseline methods for quantitative metrics, human perceptual studies and native deaf signer comprehension.","url_abs":"https://arxiv.org/abs/2203.15354v1","url_pdf":"https://arxiv.org/pdf/2203.15354v1.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":"signing-at-scale-learning-to-co-articulate","repo_url":"https://github.com/bensaunders27/meinedgs-translation-protocols","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sign-language-production","task_name":"Sign Language Production"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.15354","atlas_url":"https://app.syntology.ai/?focus=2203.15354","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}