3 papers
cs.CV2025
HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution
Chao Yang, Boqian Zhang, Jinghao Xu +1
Diffusion-based methods have shown great promise in single image super-resolution (SISR); however, existing approaches often produce blurred fine details due to insufficient guidan…
cs.CV2025
DeltaDiff: Reality-Driven Diffusion with AnchorResiduals for Faithful SR
Chao Yang, Yong Fan, Qichao Zhang +2
Recently, the transfer application of diffusion models in super-resolu-tion tasks has faced the problem ofdecreased fidelity. Due to the inherent randomsampling characteristics ofd…
cs.CV2025
GVTNet: Graph Vision Transformer For Face Super-Resolution
Chao Yang, Yong Fan, Cheng Lu +2
Recent advances in face super-resolution research have utilized the Transformer architecture. This method processes the input image into a series of small patches. However, because…