SpecTrHuMS: Spectral transformer for human mesh sequence learning

• Published in: Computers & graphics Vol. 115; pp. 191 - 203
• Main Authors: Lemeunier, Clément, Denis, Florence, Lavoué, Guillaume, Dupont, Florent
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2023; Elsevier
• Subjects: Autoencoder; Computer Science; Computer Vision and Pattern Recognition; Geometric deep learning; Human body triangular mesh sequences; Machine Learning; Spectral analysis; Transformers; Transformers; Geometric deep learning; Autoencoder; Human body triangular mesh sequences; Spectral analysis; Geometric Deep Learning

We present SpecTrHuMS, a Spectral Transformer for 3D triangular Human Mesh Sequence learning which combines known deep learning models with spectral mesh processing to capture characteristics of 3D shapes as well as temporal dependencies between the frames. Unlike previous works in this field, our a...