Blakey Wu

HPSv2. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

align_sd. Better Aligning Text-to-Image Models with Human Preference. ICCV 2023

CORA. A DETR-style framework for open-vocabulary detection (OVD). CVPR 2023

wikiscenes. Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision. ICCV 2021.

VideoFlow. Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

Front-end-Homework. front-end final work by cocosStudio