Avatar

Xuanchi Ren

Student

University of Toronto

Biography

I am a PhD student at University of Toronto. I am also a research scientist at NVIDIA. My supervisor is Prof. Sanja Fidler. During my undergraduate years at HKUST, I was supervised by Prof. Qifeng Chen and I was fortunate to work with Dr. Li Erran Li, Prof. Alexandre Alahi@EPFL, Dr. Yuwang Wang@MSRA and Prof. Xiaolong Wang@UCSD.

My research interests are in computer vision, particularly generative modeling and 3D vision.

Interests

  • Computer Vision
  • Deep Learning

Education

  • PhD student in Computer Science, 2022-Now

    University of Toronto

  • Exchange student, 2020 Spring

    EPFL

  • BSc in Compter Science and Math, 2017-2022

    HKUST

Publications

Xuanchi Ren*, Yifan Lu*, Tianshi Cao*, Ruiyuan Gao*, Shengyu Huang, Amirmojtaba Sabour, Tianchang Shen, Tobias Pfaff, Jay Zhangjie Wu, Runjian Chen, Seung Wook Kim, Jun Gao, Laura Leal-Taixe, Mike Chen, Sanja Fidler, Huan Ling (2025). Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models. White Paper.

PDF Website

Xuanchi Ren*, Tianchang Shen*, Jiahui Huang, Huan Ling, Yifan Lu, Merlin Nimier-David, Thomas Müller, Alexander Keller, Sanja Fidler, Jun Gao (2025). GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control. CVPR 2025 Highlight (3% acceptance rate).

PDF Website

NVIDIA (2025). Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control. White Paper (Core Contributor; Featured in Jensen Huang's GTC 2025 keynote).

PDF Website

Jay Zhangjie Wu*, Yuxuan Zhang*, Haithem Turki, Xuanchi Ren, Jun Gao, Mike Zheng Shou, Sanja Fidler, Zan Gojcic†, Huan Ling† (2025). Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models. CVPR 2025 Best Paper Award Candidate (Top 14).

PDF Website

Yifan Lu*, Xuanchi Ren*, Jiawei Yang, Tianchang Shen, Zhangjie Wu, Jun Gao, Yue Wang, Siheng Chen, Mike Chen, Sanja Fidler, Jiahui Huang (2025). InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models. ICCV 2025.

PDF Website

Xuanchi Ren*, Yifan Lu*, Hanxue Liang, Jay Zhangjie Wu, Huan Ling, Mike Chen, Sanja Fidler, Francis Williams, Jiahui Huang (2024). SCube: Instant Large-Scale Scene Reconstruction using VoxSplats. NeurIPS 2024.

Website

Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams (2023). XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies. CVPR 2024 Highlight (2.8% acceptance rate).

PDF Website

Chenyang Lei*, Xuanchi Ren*, Zhaoxiang Zhang, Qifeng Chen (2023). Blind Deflickering by Neural Filtering with a Flawed Atlas. CVPR 2023.

PDF Website

Xuanchi Ren, Xiaolong Wang (2022). Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image. CVPR 2022.

PDF Website

Xuanchi Ren*, Tao Yang*, Yuwang Wang, Wenjun Zeng (2021). Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View. ICLR 2022.

PDF Code

Dacheng Yin*, Xuanchi Ren*, Chong Luo, Yuwang Wang, Zhiwei Xiong, Wenjun Zeng (2021). Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph. ICLR 2022.

PDF Website

Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng (2021). Towards Building A Group-based Unsupervised Representation Disentanglement Framework. ICLR 2022.

PDF Code

Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng (2021). Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement. ICCV Workshop 2021.

PDF Code

Xuanchi Ren*, Tao Yang*, Li Erran Li, Alexandre Alahi, Qifeng Chen (2021). Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving. ICCV 2021.

PDF Code

Xuanchi Ren*, Zian Qian*, Qifeng Chen (2020). Video Deblurring by Fitting to Test Data. Preprint.

PDF Code Website

Xuanchi Ren, Haoran Li, Zijian Huang, Qifeng Chen (2019). Self-supervised Dance Video Synthesis Conditioned on Music. ACM MM 2020. Full Oral Presentation (9% acceptance rate).

PDF Code

Projects

Innovate the Retail Industry with Automatic Checkout System
Xuanchi Ren, Zian Qian, Zhiwei Wang
PDF
On the Performance Benefits of Zeroth Order Methods in the Context of Adversarial Training
XAlice Biryukov, Nicolas Dutly, Xuanchi Ren