Yuanbo Yang

ReRoPE: Repurposing RoPE for Relative Camera Control

Chunyang Li*, Yuanbo Yang*, Jiahao Shao*, Hongyu Zhou, Katja Schwarz, Yiyi Liao

SIGGRAPH 2026

Project arXiv

ReRoPE repurposes Rotary Position Embedding for shift-invariant relative camera control in video generation.

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

Jiaxin Huang, Yuanbo Yang, Bangbang Yang, Lin Ma, Yuewen Ma, Yiyi Liao

CVPR 2026

Project arXiv

Gen3R bridges foundational reconstruction models and video diffusion models for scene-level 3D generation.

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

Yuanbo Yang*, Jiahao Shao*, Xinyang Li, Yujun Shen, Andreas Geiger, Yiyi Liao

CVPR 2025

Project arXiv Code

Prometheus introduces feed-forward scene-level 3D generation in seconds, harnessing pre-trained 2D priors for generalizable and efficient 3D synthesis.

UrbanGen: Urban Generation with Compositional and Controllable Neural Fields

Yuanbo Yang, Yujun Shen, Yue Wang, Andreas Geiger, Yiyi Liao

T-PAMI 2025

Project Paper

UrbanGen generates 3D urban radiance fields with photorealistic rendering, accurate geometry, high controllability, and diverse city styles.

ChronoDepth: Learning Temporally Consistent Video Depth from Video Diffusion Priors

Jiahao Shao*, Yuanbo Yang*, Hongyu Zhou, Youmin Zhang, Yujun Shen, Vitor Guizilini, Yue Wang, Matteo Poggi, Yiyi Liao

CVPR 2025

Project arXiv Code

ChronoDepth addresses temporally consistent video depth estimation using video diffusion model priors.

Orientation Matters: Making 3D Generative Models Orientation-Aligned

Yichong Lu*, Yuzhuo Tian*, Zijin Jiang*, Yikun Zhao, Yuanbo Yang, Hao Ouyang, Haoji Hu, Huimin Yu, Yujun Shen, Yiyi Liao

NeurIPS 2025

Project

Orientation Matters addresses orientation alignment in 3D generative models.

HeFT: Harnessing Video Diffusion Priors for Robust Correspondence

Tianyu Yuan*, Yuanbo Yang*, Lin-Zhuo Chen, Yao Yao, Zhuzhong Qian

arXiv 2025

Project arXiv

HeFT is a zero-shot point tracking framework leveraging visual priors of pretrained video diffusion models.

The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving

Jiabao Wang, Hongyu Zhou, Yuanbo Yang, Jiahao Shao, Yiyi Liao

arXiv 2025

arXiv

The Constant Eye benchmarks appearance robustness under OOD conditions in autonomous driving.

TeFF: Learning 3D-Aware GANs from Unposed Images with Template Feature Field

Xinya Chen, Hanlei Guo, Yanrui Bin, Shangzhan Zhang, Yuanbo Yang, Hongyu Zhou, Youmin Zhang, Yujun Shen, Yiyi Liao

ECCV 2024 (Oral)

Project arXiv Code

TeFF learns 3D-aware GANs from unposed images via on-the-fly pose estimation with a learned template feature field.

MaPa: Text-driven Photorealistic Material Painting for 3D Shapes

Shangzhan Zhang, Sida Peng, Tao Xu, Yuanbo Yang, Tianrun Chen, Nan Xue, Yujun Shen, Hujun Bao, Ruizhen Hu, Xiaowei Zhou

SIGGRAPH 2024

Project Paper

MaPa creates segment-wise procedural material graphs for high-quality rendering with significant editing flexibility.

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

Yuanbo Yang, Yifei Yang, Hanlei Guo, Rong Xiong, Yue Wang, Yiyi Liao

ICCV 2023

Project arXiv

UrbanGIRAFFE leverages coarse 3D panoptic priors to guide a 3D-aware generative model for photorealistic urban scene synthesis with diverse controllability.

Yuanbo Yang 杨渊博

Research

Experience

UC San Diego

Zhejiang University

Hangzhou Dianzi University

Analemma AI

University of Michigan

Ant Group