Visual content generation has achieved great success in the past few years, but current visual generation models still lack controllability and compositionality. In real applications, we desire highly controllable visual generation models which allow users to control the generated contents in a fine-grained manner. We also desire models which can effectively compose objects with different attributes and relationships into a complex and coherent scene. In this talk, I will introduce our several works towards controllable and compositional visual content generation. I will introduce T2I-CompBench for benchmarking compositional text-to-image generation. I will also introduce our recent works on drag-based video editing, controllable 3D generation, and training-free massive concept editing in text-to-image diffusion models.
Professor Xihui Liu is an Assistant Professor at the Department of Electrical and Electronic Engineering and Institute of Data Science, The University of Hong Kong. Before joining HKU, she was a postdoc Scholar at UC Berkeley, advised by Professor Trevor Darrell. She obtained her Ph.D. degree from Multimedia Lab (MMLab), the Chinese University of Hong Kong, and received her bachelor’s degree from Tsinghua University. Her research interests cover computer vision, machine learning, and artificial intelligence. She serves as area chair for CVPR 2024 and ACM MM 2024, and she was awarded Adobe Research Fellowship 2020, MIT EECS Rising Stars 2021, and WAIC Rising Stars Award 2022.
Clean water and clean air are vital for public health. This project focuses on developing high-efficiency and environmentally sustainable filters for removing harmful air/water pollutants. The team has developed novel architectures and functionalities for the filters to achieve high permeance, high removal efficiency, and excellent reusability.
