GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration Paper • 2605.31039 • Published May 29 • 46
Image/Video Restoration, Enhancement and Quality Assessment Collection This collection hosts VCLab's leading research in visual restoration, enhancement, and quality assessment, especially in real-world scenarios. • 22 items • Updated May 14
3D Perception, Reconstruction and Generation Collection This collection gathers VCLab's research to sense, reconstruct, synthesize, and edit high-fidelity 3D worlds. • 6 items • Updated May 14
Benchmarks and Datasets Collection This comprehensive collection hosts PolyU VCLab's contributions to the evaluation benchmarks and training datasets for visual computing. • 3 items • Updated Apr 22
Architecture and Training Paradigms Collection This collection showcases VCLab's investigations on new architectures of vision transformers, LLMs, VLMs and their training paradigms. • 5 items • Updated Apr 22
3D Perception, Reconstruction and Generation Collection This collection gathers VCLab's research to sense, reconstruct, synthesize, and edit high-fidelity 3D worlds. • 6 items • Updated May 14