Yuan Liu - Homepage

Yuan Liu (刘缘)

Incoming Assistant Professor@HKUST, PostDoc@NTU, PhD@HKU

yuanly@ust.hk

I'm visiting NTU as a PostDoc working with Prof. Ziwei Liu. I obtained my PhD degree at HKU advised by Prof. Wenping Wang and Prof. Taku Komura. I'm one of the organizers of AnySyn3D. My research mainly concentrates on 3D vision and graphics. I currently work on topics about 3D AIGC including neural rendering, neural representations, and 3D generative models.

[Github] [Twitter] [Google Scholar]

Openings

I will join ISD HKUST as an assistant professor in 2025 spring, leading the Intelligent Graphics Lab. We are recruiting passionate PhD and visiting students from across the globe to join our research team! We especially welcome international students with a strong drive and a solid background in related fields.

We are currently working on the following topics.

3D representations (like NeuS, NeRF, 3D GS).
3D asset generation.
3D-aware video generation.

Some recent works can be found in the Publications section. If you are interested in working with me on these topics, please fill the Google form here and drop an email to yuanly@ust.hk. I have experience in mentoring master or junior PhD students. Refer to the Mentoring section for more details.

Join Us at HKUST! Are you passionate about 3D vision and graphics? At HKUST, one of Asia's top universities, you'll have the opportunity to engage in groundbreaking research alongside world-class faculty in a vibrant, innovative environment. We warmly welcome students from all over the world to join our diverse and inclusive community.

We offer a competitive monthly stipend of 19,700 HKD (around 2,500 USD) to support your academic journey. Exceptional candidates are also encouraged to apply for the prestigious HKPFS, which provides an enhanced stipend of 28,000 HKD (approximately 3,600 USD). With these scholarships, you’ll enjoy an excellent quality of life in Hong Kong while advancing your research and shaping the future of 3D technology. We can't wait to welcome you to our thriving research community!

Selected Publications (Google Scholar)

*Equal contribution †Corresponding author

	Align3R: Aligned Monocular Depth Estimation for Dynamic Videos Jiahao Lu, Tianyu Huang, Peng Li, Zhiyang Dou, Cheng Lin, Zhiming Cui, Zhen Dong, Sai-Kit Yeung, Wenping Wang, Yuan Liu† arXiv 2024 [Paper] [Project Page] [Code]
	VistaDream: Sampling multiview consistent images for single-view scene reconstruction Haiping Wang, Yuan Liu†, Ziwei Liu, Wenping Wang, Zhen Dong†, Bisheng Yang arXiv 2024 [Paper] [Project Page] [Code]
	Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention Peng Li, Yuan Liu, Xiaoxiao Long†, Feihu Zhang, Cheng Lin, Mengfei Li, Xingqun Qi, Shanghang Zhang, Wei Xue, Wenhan Luo, Ping Tan, Wenping Wang, Qifeng Liu, Yike Guo† NeurIPS 2024 [Paper] [Project Page] [Code]
	SyncDreamer: Generating Multiview-consistent Images from a Single-view Image Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long†, Lingjie Liu, Taku Komura, Wenping Wang† ICLR 2024 (Spotlight) [Paper] [Project Page] [Code]
	Wonder3D: Single Image to 3D using Cross-Domain Diffusion Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin†, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, Wenping Wang† CVPR 2024 (Highlight) [Paper] [Project Page] [Code]
	NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images Yuan Liu, Peng Wang, Cheng Lin, Xiaoxiao Long, Jiepeng Wang, Lingjie Liu, Taku Komura, Wenping Wang SIGGRAPH 2023 (TOG) [Paper] [Project Page] [Code]
	F²NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories Peng Wang, Yuan Liu, Zhaoxi Chen, Ziwei Liu, Lingjie Liu, Taku Komura, Christian Theobalt, Wenping Wang CVPR 2023 (Highlight) [Paper] [Project Page] [Code]
	Neural Rays for Occlusion-aware Image-based Rendering Yuan Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, Wenping Wang CVPR 2022 [Paper] [Project Page] [Code]
	NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, Wenping Wang NeurIPS 2021 (Spotlight) [Paper] [Project Page] [Code]

Mentoring

I spent wonderful time working with talented master or junior PhD students on some interesting research projects as follows.

Haiping Wang: YOHO (MM'22), RoReg (TPAMI'23) SGHR (CVPR'23) FreeReg (ICLR'23)

PhD at WHU.

Runsong Zhu: AdaFit (ICCV'21)

Master at WHU, Ph.D. at CUHK

Yuqing Zhang: DreamMat (SIGGRAPH'24)

Master at ZJU

Jionghao Wang: SO-SMPL (ECCV'24)
- Master at SJTU, PhD at TAMU
Peng Li: Era3D (NeurIPS'24)
- PhD at HKUST
Wenqi Jiangying: GaussianShader (CVPR'24)
- PhD at ShanghaiTech University
Anran Liu: NeRFBuff (TVCG'24), Part123 (SIGGRAPH'24)
- PhD at HKU

	Align3R: Aligned Monocular Depth Estimation for Dynamic Videos Jiahao Lu, Tianyu Huang, Peng Li, Zhiyang Dou, Cheng Lin, Zhiming Cui, Zhen Dong, Sai-Kit Yeung, Wenping Wang, Yuan Liu† arXiv 2024 [Paper] [Project Page] [Code]
	VistaDream: Sampling multiview consistent images for single-view scene reconstruction Haiping Wang, Yuan Liu†, Ziwei Liu, Wenping Wang, Zhen Dong†, Bisheng Yang arXiv 2024 [Paper] [Project Page] [Code]
	Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention Peng Li, Yuan Liu, Xiaoxiao Long†, Feihu Zhang, Cheng Lin, Mengfei Li, Xingqun Qi, Shanghang Zhang, Wei Xue, Wenhan Luo, Ping Tan, Wenping Wang, Qifeng Liu, Yike Guo† NeurIPS 2024 [Paper] [Project Page] [Code]
	SyncDreamer: Generating Multiview-consistent Images from a Single-view Image Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long†, Lingjie Liu, Taku Komura, Wenping Wang† ICLR 2024 (Spotlight) [Paper] [Project Page] [Code]
	Wonder3D: Single Image to 3D using Cross-Domain Diffusion Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin†, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, Wenping Wang† CVPR 2024 (Highlight) [Paper] [Project Page] [Code]
	NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images Yuan Liu, Peng Wang, Cheng Lin, Xiaoxiao Long, Jiepeng Wang, Lingjie Liu, Taku Komura, Wenping Wang SIGGRAPH 2023 (TOG) [Paper] [Project Page] [Code]
	F²NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories Peng Wang, Yuan Liu, Zhaoxi Chen, Ziwei Liu, Lingjie Liu, Taku Komura, Christian Theobalt, Wenping Wang CVPR 2023 (Highlight) [Paper] [Project Page] [Code]
	Neural Rays for Occlusion-aware Image-based Rendering Yuan Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, Wenping Wang CVPR 2022 [Paper] [Project Page] [Code]
	NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, Wenping Wang NeurIPS 2021 (Spotlight) [Paper] [Project Page] [Code]