Xiaoyang Guo

Xiaoyang Guo (郭晓阳)

I work on embodied foundation models that unify understanding, simulation, and action. Previously, I was a Principal Researcher at Horizon Robotics, where I led work on 3D reconstruction, digital twins, and interactive driving simulation. I received my Ph.D. from the Multimedia Laboratory (MMLab) at The Chinese University of Hong Kong, where I was fortunate to be advised by Prof. Xiaogang Wang and Prof. Hongsheng Li. Prior to that, I obtained my Bachelor's degree in Computer Science from Tsinghua University.

My research interests include large-scale 3D scene understanding (multi-view reconstruction, Gaussian Splatting, and VGGT), high-precision 3D reconstruction and digital twins for autonomous driving, and embodied foundation models.

I am actively seeking highly motivated interns to collaborate on projects involving embodied foundation models, 3D foundation models, and generative simulation. If you're interested, feel free to reach out via email.

Email / CV / Scholar / Github

News

2026.06: One paper accepted to ICML 2026 (EPS3D). SCOPE released on arXiv.
2026.04: Four papers accepted to CVPR 2026: Scal3R (Highlight), LongStream, LiteVGGT, and VGGT4D.
2026.03: CompoSIA accepted to ECCV 2026. Started working on embodied foundation models.
2026.02: SAIL-Recon accepted as an Oral at 3DV 2026.
2025.10: Three papers at ICCV 2025 (Epona, DM-Calib, StableDepth Highlight); RAD at NeurIPS 2025; SynthDrive and ComDrive at IROS 2025.

Selected Publications * equal contribution; † project lead. Full list on Google Scholar.
	SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry Zheng Zhang, Lihe Yang, Tianyu Yang, Chaohui Yu, Yixing Lao, Xiaoyang Guo, Biao Gong, Fan Wang, Hengshuang Zhao Preprint, Arxiv'26 [arXiv]
	EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation Runsong Zhu, Jiaxin Guo, Xiaoyang Guo^†, Zhengzhe Liu, Ka-Hei Hui, Wei Yin, Kai Chen, Wei Chen, Weiqiang Ren, Yunhui Liu, Pheng-Ann Heng, Chi-Wing Fu International Conference on Machine Learning, ICML'26 [arXiv] [code]
	HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding, Xianda Chen, Yuansen Du, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Zhengqing Chen, Hao Wang Preprint, Arxiv'26 [arXiv]
	HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation Conglang Zhang, Yifan Zhan, Qingjie Wang, Zhanpeng Ouyang, Yu Li, Zihao Yang, Xiaoyang Guo, Weiqiang Ren, Qian Zhang, Zhen Dong, Yinqiang Zheng, Wei Yin, Zhengqing Chen Preprint, Arxiv'26 [arXiv]
	Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation Yifan Zhan, Zhengqing Chen, Qingjie Wang, Zhuo He, Muyao Niu, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Yinqiang Zheng European Conference on Computer Vision, ECCV'26 [arXiv] [project page] [code]
	Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction Tao Xie, Peishan Yang, Yudong Jin, Yingfeng Cai, Wei Yin, Weiqiang Ren, Qian Zhang, Wei Hua, Sida Peng, Xiaoyang Guo^†, Xiaowei Zhou^† Conference on Computer Vision and Pattern Recognition, CVPR'26 (Highlight) [arXiv] [project page] [code]
	LongStream: Long-Sequence Streaming Autoregressive Visual Geometry Chong Cheng, Xianda Chen, Tao Xie, Wei Yin, Weiqiang Ren, Qian Zhang, Xiaoyang Guo^†, Hao Wang Conference on Computer Vision and Pattern Recognition, CVPR'26 [arXiv] [project page]
	LiteVGGT: Boosting Vanilla VGGT via Geometry-Aware Cached Token Merging Zhijian Shu, Cheng Lin, Tao Xie, Wei Yin, Ben Li, Zhiyuan Pu, Weize Li, Yao Yao, Xun Cao, Xiaoyang Guo, Xiao-Xiao Long Conference on Computer Vision and Pattern Recognition, CVPR'26 [arXiv] [project page]
	VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction Yu Hu^, Chong Cheng^, Sicheng Yu^, Xiaoyang Guo, Hao Wang Conference on Computer Vision and Pattern Recognition, CVPR'26* [arXiv] [project page] [code]
	SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis Zhengqing Chen, Ruohong Mei, Xiaoyang Guo^†, Qingjie Wang, Yubin Hu, Wei Yin, Weiqiang Ren, Qian Zhang International Conference on Intelligent Robots and Systems, IROS'25 [paper] [video]
	ComDrive: Comfort-Oriented End-to-End Autonomous Driving Junming Wang, Xingyu Zhang, Zebin Xing, Songen Gu, Xiaoyang Guo, Yang Hu, Ziying Song, Qian Zhang, Xiaoxiao Long, Wei Yin International Conference on Intelligent Robots and Systems, IROS'25 [arXiv] [project page]
	SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization Junyuan Deng, Heng Li, Tao Xie, Weiqiang Ren, Qian Zhang, Ping Tan, Xiaoyang Guo^† International Conference on 3D Vision, 3DV'26 (Oral) [arXiv] [project page] [code]
	RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-Based Reinforcement Learning Hao Gao, Shaoyu Chen, Bo Jiang, Bencheng Liao, Yiang Shi, Xiaoyang Guo, Yuechuan Pu, Haoran Yin, Xiangyu Li, Xinbang Zhang, Ying Zhang, Wenyu Liu, Qian Zhang, Xinggang Wang Advances in Neural Information Processing Systems, NeurIPS'25 [arXiv] [project page]
	Epona: Autoregressive Diffusion World Model for Autonomous Driving Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan, Xiaoyang Guo, Yuan Liu, Jingwei Huang, Li Yuan, Qian Zhang, Xiaoxiao Long, Xun Cao, Wei Yin International Conference on Computer Vision, ICCV'25 [arXiv] [project page] [code]
	Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration Junyuan Deng, Wei Yin, Xiaoyang Guo^†, Qian Zhang, Xiaotao Hu, Weiqiang Ren, Xiao-Xiao Long, Ping Tan International Conference on Computer Vision, ICCV'25 [arXiv] [code]
	DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT Xiaotao Hu, Wei Yin, Mingkai Jia, Junyuan Deng, Xiaoyang Guo, Qian Zhang, Xiaoxiao Long, Ping Tan Preprint, Arxiv'24 [arXiv]
	StableDepth: Scene-Consistent and Scale-Invariant Monocular Depth Zheng Zhang, Lihe Yang, Tianyu Yang, Chaohui Yu, Xiaoyang Guo, Yixing Lao, Hengshuang Zhao International Conference on Computer Vision, ICCV'25 (Highlight) [project page] [paper]
	NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis Yubin Hu^, Xiaoyang Guo^, Yang Xiao, Jingwei Huang, Yong-Jin Liu European Conference on Computer Vision, ECCV'24 (Realtime streamed on Petal Map App) [arXiv] [paper]
	SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset Yubin Hu, Kairui Wen, Heng Zhou, Xiaoyang Guo, Yong-Jin Liu Advances in Neural Information Processing Systems, NeurIPS'24 (DB Track) [arXiv] [project page] [dataset]
	ArrangementNet: Learning Scene Arrangements for Vectorized Indoor Scene Modeling Jingwei Huang, Shanshan Zhang, Bo Duan, Xiaoyang Guo, Minwei Sun, Li Yi ACM Transactions on Graphics (TOG) , TOG'23 (Journal Track) [paper]
	LIGA-Stereo: Learning Lidar Geometry aware Representations for Stereo-based 3d Detector Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li International Conference on Computer Vision), ICCV'21 (Ranked 1st place among stereo-based 3D detection methods on KITTI (July 2021), refer to here.) [arXiv] [project page] [paper] [code]
	Group-wise Correlation Stereo Network Xiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, Hongsheng Li Conference on Computer Vision and Pattern Recognition, CVPR'19 [arXiv] [paper] [code]
	Unsupervised Cross-Spectral Stereo Matching by Learning to Synthesize Xiaoyang Guo^, Mingyang Liang^, Hongsheng Li, Xiaogang Wang, You Song AAAI, AAAI'19 (Oral Presentation) [arXiv] [paper]
	Learning Monocular Depth by Distilling Cross-domain Stereo Networks Xiaoyang Guo, Hongsheng Li, Shuai Yi, Jimmy Ren, Xiaogang Wang European Conference on Computer Vision, ECCV'18 [arXiv] [paper] [video] [code]
	Neural Network Encapsulation Hongyang Li, Xiaoyang Guo, Bo Dai, Wanli Ouyang, Xiaogang Wang European Conference on Computer Vision, ECCV'18 [arXiv] [paper]

Thanks for the template from Jon Barron .

News

Selected Publications