Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Enhanced Deformable Convolution with Center-invariant Offset and Edge-aware Mask
Yixiao Li, Xiaoyuan Yang, Jin Jiang +5
Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exceptional capabilities in dyna…
cs.CV2026
GSPan: A Continuous Gaussian Primitive Representation for Arbitrary-Scale Pansharpening
Fangyi Li, Xiaoyuan Yang, Yixiao Li +3
Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and panchromatic (PAN) observations. Most existing deep lea…
eess.IV2026
Perceptual Quality Optimization of Image Super-Resolution
Wei Zhou, Yixiao Li, Hadi Amirpour +4
Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which…