I am a tenure-track research professor in Zhejiang University. Before that, I was a Postdoc in Autonomous Vision Group, a part of the University of Tübingen and the MPI for Intelligent Systems, working with Prof. Andreas Geiger. I received my Ph.D. in Control Science and Engineering from Zhejiang University in June 2018 and the B.S. degree from Xi’an Jiaotong University in 2013.
My research interest lies in 3D computer vision, including 3D scene understanding, 3D reconstruction, depth estimation and 3D controllable image synthesis.
For prospective students interested in computer vision, feel free to contact me via email!
|Sep 29, 2021||Two papers (1 oral, 1 poster) are accepted to NeurIPS 2021.|
|Jun 24, 2021||Our work SMD-Nets was featured on the CVPR Daily and the BEST OF CVPR of Computer Vision News.|
|Jun 2, 2021||I will be joining Zhejiang University as a tenure-track assistant professor this September!|
|May 31, 2021||I will serve as an Area Chair for BMVC 2021.|
|May 20, 2021||I was acknowledged as Outstanding Reviewer at CVPR 2021.|
Full publication list can be found on Google Scholar.
*equal contribution; ♯corresponding author.
Shape As Points: A Differentiable Poisson SolverIn Advances in Neural Information Processing Systems (NeurIPS) 2021
On the Frequency Bias of Generative ModelsIn Advances in Neural Information Processing Systems (NeurIPS) 2021
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DArxiv 2021
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPsIn Proc. of the IEEE International Conf. on Computer Vision (ICCV) 2021
SMD-Nets: Stereo Mixture Density NetworksIn Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2021
Learning Steering Kernels for Guided Depth CompletionIEEE Trans. on Image Processing (TIP) 2021
GRAF: Generative Radiance Fields for 3D-Aware Image SynthesisIn Advances in Neural Information Processing Systems (NeurIPS) 2020
Towards Unsupervised Learning of Generative Models for 3D Controllable Image SynthesisIn Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2020
Connecting the Dots: Learning Representations for Active Monocular Depth EstimationIn Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2019
Deep Marching Cubes: Learning Explicit Surface RepresentationsIn Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2018
On the Integration of Optical Flow and Action RecognitionIn German Conference on Pattern Recognition (GCPR) 2018
Graph Regularized Auto-encoders for Image RepresentationIEEE Trans. on Image Processing (TIP) 2017
Place Classification with a Graph Regularized Deep Neural NetworkIEEE Trans. on Cognitive and Developmental Systems (TCDS) 2017
Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser ObservationIn Proc. of the IEEE International Conf. on Robotics and Automation (ICRA) 2017
Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural NetworksIn Proc. of the IEEE International Conf. on Robotics and Automation (ICRA) 2016