3 papers
cs.CV2026
Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution
Ren Wang, Yung-Yu Chuang
The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realis…
cs.CV2026
Reflection Separation from a Single Image via Joint Latent Diffusion
Zheng-Hui Huang, Zhixiang Wang, Yu-Lun Liu +1
Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections. Existing methods often struggle to recover both layers in glare or…
cs.CV2026
Generative World Renderer
Zheng-Hui Huang, Zhixiang Wang, Jiaming Tan +6
Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge thi…