Metraipolis › archive › dc_62cdceec7095

Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs — arXiv:2608.13368

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13368
License (as archived)
CC0-1.0
Archived
2026-10-19T04:18:30.903Z
SHA-256 of the archived text
0b5ae0fcf38a6b7da1a71810a92ee44bcaa6e61f6b511459e076fb4ce8ba0fec
Stable URL of this page
https://metraipolis.com/documento/dc_62cdceec7095

How to cite

Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs — arXiv:2608.13368 — arXiv (en), https://arxiv.org/abs/2608.13368 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62cdceec7095 (Metraipolis archive dc_62cdceec7095, sha256 0b5ae0fcf38a6b7da1a71810a92ee44bcaa6e61f6b511459e076fb4ce8ba0fec)
BibTeX
@misc{dc62cdceec7095,
  title = {Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs — arXiv:2608.13368},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13368},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62cdceec7095; sha256 0b5ae0fcf38a6b7da1a71810a92ee44bcaa6e61f6b511459e076fb4ce8ba0fec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13368. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators--global, hand, and head--each guide a corresponding expert branch in the generator toward a distinct visual region, enabling implicit feature specialization without explicit diversity losses. To stabilize this multi-discriminator system, whose early-phase training otherwise exhibits chaotic dynamics, we introduce a United Loss consensus mechanism that regularizes each discriminator toward the ensemble average at a 10% weight. Each branch further adopts a dual-pathway convolutional-transformer design with learnable AdaptiveFeatureFusion, balancing the stability of convolutions against the detail of windowed self-attention. The generator is trained using an alternating three-mode schedule (discriminator, holistic generation, branch-specialized generation). On a custom 156GB dataset with a filtered evaluation set that removes easy and repetitive samples, our 0.2B-parameter variant achieves 29.78 PSNR (0.9593 SSIM), the 0.66B variant reaches 30.52 PSNR (0.9631 SSIM) after 7.37M steps, and the 1.3B variant achieves 30.72 PSNR (0.9650 SSIM). The gain from 0.66B to 1.3B is only +0.20 PSNR despite nearly doubling the parameters, demonstrating sharply diminishing returns. Inference VRAM footprints are 1.5 GB, ~5 GB, and 8 GB respectively, enabling deployment on consumer-grade hardware. Full ablation studies remain ongoing due to the 2-3 month training cycle on a single GPU. The system was showcased at the 2025 Hong Kong Frontier Technology Summit.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.13368 — 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 2026-10-19T04:13:06.763Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).