|
Xiang (Ryan) Li
My name is Xiang Li (李想; pronounced "Shiang Li"). I am a fifth-year Ph.D. student at the University of Illinois Urbana–Champaign (UIUC), advised by Prof. James M. Rehg. My research focuses on the analysis and alignment of visual generative AI, with an emphasis on 3D generation.
In recent years, I have interned at FAIR Perception (Meta AI), working with Weiyao Wang, Sasha Sax, and Hao Tang. I also interned at Google Research with Boqing Gong. I received my bachelor's degree from The Hong Kong University of Science and Technology (HKUST), where I was advised by Prof. Yu-Wing Tai and Prof. Chi-Keung Tang.
Email /
Google Scholar /
LinkedIn
|
|
|
|
Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
Xiang Li*,
Zirui Wang*,
Zixuan Huang,
James M. Rehg
In NeurIPS, 2025 (Spotlight ✨)
paper
/
project page
We introduce Cue3D, the first comprehensive, model-agnostic framework for quantifying the influence of individual image cues in single-image 3D generation.
|
|
|
Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
Xiang Li,
Zixuan Huang,
Anh Thai,
James M. Rehg
In CVPR, 2025 (Highlight ✨)
paper
/
project page
We propose Reflect3D, a zero-shot single-image 3D reflection symmetry detector; we improve single-image 3D generation through symmetry-aware optimization.
|
|
|
Video State-Changing Object Segmentation
Jiangwei Yu*,
Xiang Li*,
Xinran Zhao,
Hongming Zhang,
Yu-Xiong Wang
In ICCV, 2023
paper
/
project page
/
dataset and code
We present a weakly-supervised Video State-Changing Object Segmentation (VSCOS) benchmark, revealing challenges in current VOS models for state-changing objects and introducing three solutions for improved state-changing object segmentation.
|
|
|
YouTubePD: A Multimodal Benchmark for Parkinson's Disease Analysis
Andy Zhou*,
Samuel Li*,
Pranav Sriram*,
Xiang Li*,
Jiahua Dong*,
Ansh Sharma,
Yuanyi Zhong,
Shirui Luo,
Maria Jaromin,
Volodymyr Kindratenko,
George Heintz,
Christopher Zallek,
Yu-Xiong Wang
In NeurIPS Datasets and Benchmarks Track, 2023
paper
/
project page
/
dataset
We introduce YouTubePD, the first public multimodal benchmark for Parkinson's Disease (PD) analysis, crowdsourced from existing YouTube videos featuring over 200 subjects.
|
|
|
One-Shot Object Detection without Fine-Tuning
Xiang Li*,
Lin Zhang*,
Yau Pun Chen,
Yu-Wing Tai,
Chi-Keung Tang
arXiv, 2020
paper
/
project page
/
code
We introduce a two-stage model and training strategies for one-shot object detection by integrating the metric learning with an anchor-free Faster R-CNN-style detection pipeline.
|
|
|
FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
Xiang Li,
Tianhan Wei,
Yau Pun Chen,
Yu-Wing Tai,
Chi-Keung Tang
In CVPR, 2020
paper
/
dataset and code
A few-shot segmentation dataset containing 1000 varied and balanced object categories with pixelwise annotation of ground-truth segmentation.
|
|
