Metraipolis › archive › dc_b400bd7aa033

SignRR: Retrieve and Refine Real Motion for Sign Language Production — arXiv:2608.28568

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28568
License (as archived): CC0-1.0
Archived: 2026-10-17T11:33:21.786Z
SHA-256 of the archived text: d0f34b73c5cf3c6b8ad8744abae7fc8e5fbf2cca0f7aab80aa4cbcfc6d8f604d
Stable URL of this page: https://metraipolis.com/documento/dc_b400bd7aa033

How to cite

SignRR: Retrieve and Refine Real Motion for Sign Language Production — arXiv:2608.28568 — arXiv (en), https://arxiv.org/abs/2608.28568 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b400bd7aa033 (Metraipolis archive dc_b400bd7aa033, sha256 d0f34b73c5cf3c6b8ad8744abae7fc8e5fbf2cca0f7aab80aa4cbcfc6d8f604d)

BibTeX

@misc{dcb400bd7aa033,
  title = {SignRR: Retrieve and Refine Real Motion for Sign Language Production — arXiv:2608.28568},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28568},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b400bd7aa033; sha256 d0f34b73c5cf3c6b8ad8744abae7fc8e5fbf2cca0f7aab80aa4cbcfc6d8f604d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28568. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainly follows two paradigms. Generative models synthesize motion from a learned prior or from noise, without reference to an observed signing instance, making rare hand configurations and signer-specific articulation difficult to preserve. Retrieval-based methods reuse real, well-articulated motion segments, but concatenating segments from different signers and co-articulation contexts can introduce rhythm and style inconsistencies across the full sequence, not only at segment boundaries. These limitations suggest a complementary solution: use retrieval to provide realistic articulation, and use learned refinement to impose the global coherence that retrieval alone lacks. We therefore propose retrieve-and-refine, a paradigm that starts from real retrieved motion and refines it into a globally coherent signing sequence rather than generating motion from scratch. Our framework, SignRR, initializes motion from a dictionary of real sign segments and refines the full sequence with a part-aware Residual VQ-VAE, where residual quantization preserves fine hand articulation and temporal length differences are handled in the latent space. Experiments on PHOENIX14T and CSL-Daily show that SignRR achieves state-of-the-art back-translation performance while maintaining competitive pose quality.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28568 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T11:10:05.341Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).