KANMultiSign: Multi-scale sequence-based pose animation from sign language notation with Kolmogorov-Arnold networks

Sign language production from symbolic notation offers a scalable route to accessible sign animation. We present KANMultiSign, a multi-scale sequence generator that translates HamNoSys notation into two-dimensional human pose sequences. Our framework makes two complementary contributions. First, we introduce a coarse-to-fine generation strategy with multi-scale supervision: the model is first guided by an intermediate body–hand–face scaffold to encourage global structural coherence, and then refines fine-grained hand articulation to improve finger-level detail. Second, we investigate integrating Kolmogorov–Arnold Network modules into a Transformer backbone, using learnable univariate function primitives to model the highly non-linear mapping from discrete phonological symbols to continuous body kinematics with a compact parameterization. Experiments on multiple public corpora spanning Polish, German, Greek, and French sign languages show consistent reductions in dynamic time warping based joint error compared with a strong notation-to-pose baseline, while using substantially fewer parameters. Controlled ablations further indicate that KAN-based variants substantially reduce parameter count while maintaining competitive performance when coupled with multi-scale supervision, rather than serving as the main driver of accuracy gains. These findings position multi-scale supervision as the key mechanism for improving notation-conditioned pose generation, with KAN offering a compact alternative for efficient modeling. Our code will be publicly available. • Presents KANMultiSign, a Kolmogorov–Arnold Network (KAN) based multi-scale model for pose animation from HamNoSys sign notation. • Employs a coarse-to-fine pathway in which a 25-part skeleton guides detailed 137-keypoint synthesis. • Shows that multi-scale supervision is the main source of motion-accuracy improvement across multiple sign language datasets. • Investigates KAN-based FFNs as a parameter-efficient alternative within the multi-scale framework. • Achieves substantial parameter reduction while maintaining competitive pose-generation performance.