{"ID":2885525,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04049","arxiv_id":"2508.04049","title":"Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation","abstract":"Sign language video generation requires producing natural signing motions with realistic appearances under precise semantic control, yet faces two critical challenges: excessive signer-specific data requirements and poor generalization. We propose a new paradigm for sign language video generation that decouples motion semantics from signer identity through a two-phase synthesis framework. First, we construct a signer-independent multimodal motion lexicon, where each gloss is stored as identity-agnostic pose, gesture, and 3D mesh sequences, requiring only one recording per sign. This compact representation enables our second key innovation: a discrete-to-continuous motion synthesis stage that transforms retrieved gloss sequences into temporally coherent motion trajectories, followed by identity-aware neural rendering to produce photorealistic videos of arbitrary signers. Unlike prior work constrained by signer-specific datasets, our method treats motion as a first-class citizen: the learned latent pose dynamics serve as a portable \"choreography layer\" that can be visually realized through different human appearances. Extensive experiments demonstrate that disentangling motion from identity is not just viable but advantageous - enabling both high-quality synthesis and unprecedented flexibility in signer personalization.","short_abstract":"Sign language video generation requires producing natural signing motions with realistic appearances under precise semantic control, yet faces two critical challenges: excessive signer-specific data requirements and poor generalization. We propose a new paradigm for sign language video generation that decouples motion...","url_abs":"https://arxiv.org/abs/2508.04049","url_pdf":"https://arxiv.org/pdf/2508.04049v1","authors":"[\"Jiayi He\",\"Xu Wang\",\"Shengeng Tang\",\"Yaxiong Wang\",\"Lechao Cheng\",\"Dan Guo\"]","published":"2025-08-06T03:23:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}