Yuyang Zhao

I am currently a Ph.D. candidate in the Computer Vision and Robotic Perception (CVRP) Laboratory at National University of Singapore, under the supervision of A/P Gim Hee Lee. Currently, I am interning at GenAI, Microsoft. I received my B.E. degree from Tianjin University in 2020.

My research interests lie in AIGC and generalizable computer vision systems. Currently, I am working on controllable 3D and video generation.

Project Page / PDF / Code / Model / Data

A joint framework for general 3D and 4D generation, supporting both object-level and scene-level generation with one or three condition views.

Project Page / PDF / Code / Video

The first work to animate a single in-the-wild image into 3D video through textual motion descriptions.

SOLE is a highly generalizable open-vocabulary instance segmentor and can segment corresponding instances with various language instructions.

Project Page / PDF / Code / Demo

The first framework for generic video editing with both visual and textual clues. Make-A-Protagonist can achieve background editing, protagonist editing, and text-to-video editing with protagonist.

Extension of our ECCV 2022 paper (SHADE). This paper applies SHADE to visual domain generalization tasks, including semantic segmentation with Transformer backbone, image classification, and object detection.

AdvStyle adversarially changes the channel-wise mean and standard deviation to diversify source samples.

We introduce a dual consistency learning framework for domain generalized semantic segmentation, and propose a style hallucination module to generate pair-wise stylized samples.

The first work focuses on novel class discovery in semantic segmentation. This work addresses the co-occurrence of base, novel and background classes.

Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds
Yuyang Zhao, Na Zhao, Gim Hee Lee
BMVC, 2024
PDF

The first work on domain generalized semantic segmentation in 3D indoor scenes.

Stolen from Jon Barron