Sign Language Generation

Follow this topic Ask about this topic

Sign language generation studies how to turn text, glosses, or other signals into signed motion and video, including the hands, face, and body cues that carry meaning. Common approaches use diffusion models, autoregressive motion-token models, flow matching, or retrieval and refinement, with gloss timing and phonological features providing structure and control. Systems are evaluated on datasets such as PHOENIX14T, CSL-Daily, and How2Sign using measures of motion quality, linguistic accuracy, and back-translation. A central challenge is ensuring that visually plausible movement faithfully expresses the intended signs, especially when paired data is scarce and standard metrics may miss errors in meaning or articulation.

Latest papers

34 papers4 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning
Mar 11, 2026Jianhe Low, Alexandre Symeonidis-Herzig, Maksym Ivashechkin +2Human Motion Generation Sign Language Generation
CVSSP, University of Surrey, United Kingdom
OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis
Feb 26, 2026Junuk Cha, Jihyeon Kim, Han-Mu ParkSign Language Recognition Sign Language Generation
KAIST · KT · KETI
Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation
Aug 22, 2025Md Tariquzzaman, Md Farhan Ishmam, Saiyma Sittul Muna +2VLM Evaluation Vision-Language Models
Department of Computer Science and Engineering Islamic University of Technology, Bangladesh
SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning
Jun 9, 2025Taeryung Lee, Hyeongjin Nam, Gyeongsik Moon +1Conditional Generative Modeling Sign Language Generation
IPAI · Dept. of ECE & ASRI, Seoul National University · Dept. of CSE, Korea University

Mar 11, 2026J/K move · Enter open · S save

SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning

Jianhe Low, Alexandre Symeonidis-Herzig, Maksym Ivashechkin, Ozge Mercanoglu Sincan+1

CVSSP, University of Surrey, United Kingdom

Human Motion Generation Sign Language Generation

Open paper AskPDF arXiv

Sign Language Production (SLP) faces a fundamental trade-off: direct text-to-pose models suffer from regression-to-the-mean effects, while dictionary-retrieval methods produce disjointed transitions. To resolve this, we propose a novel training paradigm that leverages sparse keyframes to capture the underlying kinematic distribution of human signing. By generating dense motion from discrete anchors, our approach mitigates regression-to-the-mean while ensuring fluid articulation. To achieve this at scale, we introduce FAST, an ultra-efficient sign segmentation model that automatically mines precise temporal boundaries. We then present SignSparK, a Conditional Flow Matching (CFM) framework that utilizes these temporal anchors to synthesize 3D signing sequences. This keyframe-driven formulation also unlocks Keyframe-to-Pose (KF2P) generation, making precise spatiotemporal editing of signing sequences possible. Furthermore, SignSparK scales across four distinct sign languages, constituting the largest multilingual SLP framework to date, and integrates 3D Gaussian Splatting for photorealistic rendering. Extensive evaluations demonstrate that SignSparK achieves state-of-the-art across diverse SLP tasks and multilingual benchmarks. Our code is available at https://github.com/JianHe0628/SignSparK.

Latest papers

SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning

OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis

Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation

SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning