Sep 2026
VLMSNet: View Large to Measure Shape
Recent advances in single image super-resolution (SISR) have leveraged convolutional neural networks (CNNs) and vision transformers to model pixel-level statistics, often relying on increasingly complex architectures to capture spatial correlations. However, these approaches generally overlook a fundamental distinction...
Qi-Bin Zhang, Li-Cheng Liu, Ting-Yun Liu et al.
· IEEE Transactions on Image P... · 0 citations