2 papers
cs.CV2026
Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks
Cory Fan, Wenchao Zhang
In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is utilized to perform i…
cs.CV2025
Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
Wenchao Zhang, Jiahe Tian, Runze He +5
Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmark…