photo

Jiyuan Wang   王纪元

I am a second-year Ph.D.(Bachlor-straight-to-doctorate) student at Beijing Jiaotong University (BJTU) in MePro (led by Prof. Yao Zhao), supervised by Prof. Chunyu Lin. I will go to Nanyang Technological University (NTU), S-Lab, as a visiting student in 2026, supervised by Prof. Guosheng Lin.
I have completed an autonomous driving algorithm internship at Xiaomi, supervised by Quanyun Zhou. I am currently doing a VLM algorithm internship at Amap, Alibaba, supervised by Lei Sun and Xiangxiang Chu.
Prior to that, I received my undergraduate degree at Computer Science and Technology from BJTU.

  wangjiyuan@bjtu.edu.cn             Google Scholar             Github

Research Interests

My research interests focus on leveraging deep learning for 3D geometric perception. I am enthusiastic about exploring CV foundation models or tools such as GAN, Stable Diffusion, FLUX, Qwen-VL, VGGT, etc., and successfully integrating them into my research to achieve impressive results. The specific intersts are listed below:

1) Adverse conditions depth perception

2) Geometry perception with self-supervision

3) General 3D perception

Selected Publications

Preprint

From Editor to Dense Geometry Estimator
Jiyuan Wang, Chunyu Lin, Lei Sun, Rongying Liu, Lang Nie, Mingxing Li, Kang Liao, Xiangxiang Chu, Yao Zhao
[Project Page] [Paper] [Code]

Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation
Wenbo Nie, Lang Nie, Chunyu Lin, Jingwen Chen, Ke Xing, Jiyuan Wang, Kang Liao
[Paper] [Video]

DRL4AOI: A DRL Framework for Semantic-aware AOI Segmentation in Location-Based Services
Youfang Lin, Jinji Fu , Haomin Wen, Jiyuan Wang , Zhenjie Wei , Yuting Qiang, Xiaowei Mao, Liaxia Wu, Haoyuan Hu, Yuxuan Liang , Huaiyu Wan
[Paper] [Code]

2025

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
Jiyuan Wang, Chunyu Lin, Cheng Guan, Lang Nie, Jing He, Haodong Li, Kang Liao, Yao Zhao
Conference on Neural Information Processing Systems (NeurIPS)
[Paper] [Project Page] [Code]

Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline
Zhihao Zhang, Chunyu Lin, Lang Nie, JiYuan Wang, Meiqin Liu
IEEE Transactions on Intelligent Transportation Systems (TITS)
[Paper]

2024

Digging into contrastive learning for robust depth estimation with diffusion models
Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao, Yao Zhao
ACM Multimedia (ACM MM)
[Paper] [Code]

Overleafcopilot: Empowering academic writing in overleaf with large language models
Haomin Wen, Zhenjie Wei, Yan Lin, Jiyuan Wang, Yuxuan Liang, Huaiyu Wan
[Paper] [Main Page]
Web Application (4000+ Users)

WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions
Jiyuan Wang, Chunyu Lin, Lang Nie, Shujun Huang, Yao Zhao, Xing Pan, Rui Ai
IEEE International Conference on Robotics and Automation (ICRA)
[Paper] [Code]

Selected Awards

  • Research and Innovation Scholarship of BJTU(Oct. 2023. 4% awarded.)
  • China National Scholarship (Oct. 2023. 3% awarded.)
  • Highest honor of BJTU: Zhixing Scholarship (Nov. 2022. 0.2% awarded.)
  • China National Scholarship (Oct. 2022. 3% awarded.)
  • Baosteel Scholarship(Oct. 2022. 0.2% awarded.)
  • China National Scholarship (Oct. 2021. 3% awarded.)

Academic Service & Activities

Frequent Reviewer

  • International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Association for the Advancement of Artificial Intelligence (AAAI)