3D Face Reconstruction Using A Spectral-Based Graph Convolution Encoder

arXiv:2403.05218v1 Announce Type: new
Abstract: Monocular 3D face reconstruction plays a crucial role in avatar generation, with significant demand in web-related applications such as generating virtual financial advisors in FinTech. Current reconstruction methods predominantly rely on deep learning techniques and employ 2D self-supervision as a means to guide model learning. However, these methods encounter challenges in capturing the comprehensive 3D structural information of the face due to the utilization of 2D images for model training purposes. To overcome this limitation …

abstract applications arxiv avatar convolution cs.cv current deep learning deep learning techniques demand encoder face financial fintech graph guide however role supervision type virtual web