6 papers
Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment
Henglin Liu, Nisha Huang, Chang Liu +6
The aesthetic quality assessment task is crucial for developing a human-aligned quantitative evaluation system for AIGC. However, its inherently complex nature, spanning visual per…
DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO
Henglin Liu, Huijuan Huang, Jing Wang +3
Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. How…
UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution
Shian Du, Menghan Xia, Chang Liu +4
Cascaded video super-resolution has emerged as a promising technique for decoupling the computational burden associated with generating high-resolution videos using large foundatio…
PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
Shian Du, Menghan Xia, Chang Liu +5
Pre-trained video generation models hold great potential for generative video super-resolution (VSR). However, adapting them for full-size VSR, as most existing methods do, suffers…
Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition
Yifei Zhang, Chang Liu, Jin Wei +4
Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while t…
Falcon-UI: Understanding GUI Before Following User Instructions
Huawen Shen, Chang Liu, Gengluo Li +4
Pursuing human-like interaction for Graphical User Interface (GUI) agents requires understanding the GUI context and following user instructions. However, existing works typically…