I am a third year Ph.D student from the school of data science, University of Science and Technology of China. I am supervised by Prof. Xuejin Chen and working closely with Xiaoxiao Long and Wei Yin.

I am interested in Neural Rendering, Depth Estimation and Image-based 3D Reconstruction.

I am an active member of AnySyn3D, a research interest group that conducts various topics about the 3D. We could host multiple remote/onsite internships, with topics i) Neural Rendering, ii) 3DV for Robotics, iii) Autonomous Driving. If you are interested in working with us, feel free to drop me an email.

Experience

2022.12 - 2023.11, DJI Technology, Research Intern

2021.3 - 2022.1, Huawei Noah’s Ark Lab, Research Intern

2019.10 - 2020.1, Megvii Research in NanJing, Research Intern

Publication

DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos, Linhan Wang, Kai Cheng, Shuo Lei, Shengkun Wang, Wei Yin, Chenyang Lei, Xiaoxiao Long, Chang-Tien Lu, the Thirty-eighth Annual Conference on Neural Information Processing Systems (NIPS), 2024

GaussianPro: 3D Gaussian Splatting with Progressive Propagation, Kai Cheng, Xiaoxiao Long, Kaizhi Yang, Yao Yao, Wei Yin, Yuexin Ma, Wenping Wang, Xuejin Chen, the Forty-first International Conference on Machine Learning (ICML), 2024

UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving, Kai Cheng, Xiaoxiao Long, Yin Wei, Jin Wang, Zhiqiang Wu, Yuexin Ma, Kaixuan Wang, Xiaozhi Chen, Xuejin Chen, The Twelfth International Conference on Learning Representations (ICLR). 2024.

FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models, Guangkai Xu, Wei Yin, Hao Chen, Chunhua Shen, Kai Cheng, Feng Zhao, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023: 9310-9320.

The Second Monocular depth estimation Challenge Our team wins the CVPR2023 Monocular depth estimation challenge! (Serve as the first student team member) I am also response for the SLAM experiment in Metric3D, ICCV2023.

Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation, Kai Cheng, Hao Chen, Wei Yin, Guangkai Xu, Xuejin Chen. arXiv preprint arXiv:2205.02481, 2022

Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth, Guangkai Xu, Wei Yin, Hao Chen, Kai Cheng, Feng Zhao, Chunhua Shen. arXiv preprint arXiv:2202.01470, 2022.

Depth Estimation for Colonoscopy Images with Self-supervised Learning from Videos, MICCAI 2021 (early accept, top 13%), Kai Cheng, Yiting Ma, Bin Sun, Yang Li, Xuejin Chen*

LDPolypVideo Benchmark: A Large-Scale Colonoscopy Video Dataset of Diverse Polyps, MICCAI 2021, Yiting Ma, Xuejin Chen*, Kai Cheng, Yang Li, Bin Sun

Awards

Master Master’s First Class Scholarship 2020, 2021

Bachelor National Scholarship in 2017

Teaching Assistant

Image Understanding 2023,2024