Efficient face super-resolution via wavelet-based feature enhancement network
Face super-resolution aims to reconstruct a high-resolution face image from a low-resolution
face image. Previous methods typically employ an encoder-decoder structure to extract …
face image. Previous methods typically employ an encoder-decoder structure to extract …
[HTML][HTML] A Multi-Branch Feature Extraction Residual Network for Lightweight Image Super-Resolution
C Liu, X Wan, G Gao - Mathematics, 2024 - mdpi.com
Single-image super-resolution (SISR) seeks to elucidate the mapping relationships between
low-resolution and high-resolution images. However, high-performance network models …
low-resolution and high-resolution images. However, high-performance network models …
Attention-Guided Multi-scale Interaction Network for Face Super-Resolution
Recently, CNN and Transformer hybrid networks demonstrated excellent performance in
face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid …
face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid …
Human Multi-View Synthesis from a Single-View Model: Transferred Body and Face Representations
Y Feng, S Zhang, J Shu, H Zhao, G Pang… - arXiv preprint arXiv …, 2024 - arxiv.org
Generating multi-view human images from a single view is a complex and significant
challenge. Although recent advancements in multi-view object generation have shown …
challenge. Although recent advancements in multi-view object generation have shown …