English

Pose-Guided Sign Language Video GAN with Dynamic Lambda

Computer Vision and Pattern Recognition 2021-05-07 v1

Abstract

We propose a novel approach for the synthesis of sign language videos using GANs. We extend the previous work of Stoll et al. by using the human semantic parser of the Soft-Gated Warping-GAN from to produce photorealistic videos guided by region-level spatial layouts. Synthesizing target poses improves performance on independent and contrasting signers. Therefore, we have evaluated our system with the highly heterogeneous MS-ASL dataset with over 200 signers resulting in a SSIM of 0.893. Furthermore, we introduce a periodic weighting approach to the generator that reactivates the training and leads to quantitatively better results.

Keywords

Cite

@article{arxiv.2105.02742,
  title  = {Pose-Guided Sign Language Video GAN with Dynamic Lambda},
  author = {Christopher Kissel and Christopher Kümmel and Dennis Ritter and Kristian Hildebrand},
  journal= {arXiv preprint arXiv:2105.02742},
  year   = {2021}
}
R2 v1 2026-06-24T01:50:40.302Z