XINJI MAI / RESEARCH研究

Interest Entanglement: The Hidden Barrier to Blind Super-Resolution OptimizationInterest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization

arXiv2026

Junxiong Lin, Xinji Mai, Qianyu Guo, Haoran Wang, Zeng Tao, Xuan Tong, Ivy Pan, Wenqiang Zhang

Figure 2: SFR architecture with regression, perception, and shared-feature branches connected through InfoSqueeze.

Figure from the 图片来源:original paper原论文 ↗

SFR decouples fidelity and perceptual objectives through shared representations, with InfoSqueeze filtering redundant features for blind super-resolution.

SFR 通过共享表征解耦保真度与感知质量优化目标,并以 InfoSqueeze 过滤冗余特征,改善盲超分辨率的目标平衡。

Junxiong Lin, Xinji Mai, Qianyu Guo, Haoran Wang, Zeng Tao, Xuan Tong, Ivy Pan, Wenqiang Zhang. "Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization." arXiv. https://arxiv.org/abs/2606.22353