About Me

I'm a software engineer at Waymo. Before that, I was a Ph.D. student at University of Southern California, working in Computer Graphics and Immersive Technologies Lab under Prof. Ulrich Neumann.

My research focuses on computer vision, particularly 3D scene understanding and reconstruction.

Please reach out to me if you're interested in 2021 Summer Internship @ Waymo Perception.

Publications

Ph.D. Works

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

Weiyue Wang*, Qiangeng Xu*, Duygu Ceylan, Radomír Měch and Ulrich Neumann Neural Information Processing Systems (NeurIPS) paper | bibtex | code | supplementary * equal contributions

@inproceedings{wang2019DISN,
    title={DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction},
    author={Wang, Weiyue and Qiangeng, Xu and Ceylan, Duygu and Mech, Radomir and Neumann, Ulrich},
    booktitle={NeurIPS},
    year={2019}
}

3DN: 3D Deformation Network

Weiyue Wang, Duygu Ceylan, Radomír Měch and Ulrich Neumann IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 paper | bibtex | code

@inproceedings{wang20193dn,
    title={3DN: 3D Deformation Network},
    author={Wang, Weiyue and Ceylan, Duygu and Mech, Radomir and Neumann, Ulrich},
    booktitle={CVPR},
    year={2019}
}

Depth-aware CNN for RGB-D Segmentation

Weiyue Wang and Ulrich Neumann European Conference on Computer Vision (ECCV), 2018 paper | bibtex | code

@inproceedings{wang2018depthconv,
	title={Depth-aware CNN for RGB-D Segmentation},
	author={Wang, Weiyue and Neumann, Ulrich},
	booktitle={ECCV},
	year={2018}
}

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Weiyue Wang, Ronald Yu, Qiangui Huang and Ulrich Neumann IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Spotlight paper | bibtex | code

@inproceedings{wang2018sgpn,
	title={SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation},
	author={Wang, Weiyue and Yu, Ronald and Huang, Qiangui and Neumann, Ulrich},
	booktitle={CVPR},
	year={2018}
}

Recurrent Slice Networks for 3D Segmentation on Point Clouds

Qiangui Huang, Weiyue Wang and Ulrich Neumann IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Spotlight paper | bibtex | code

@inproceedings{huang2018rsnet,
	title={Recurrent Slice Networks for 3D Segmentation on Point Clouds},
	author={Huang, Qiangui and Wang, Weiyue and Neumann, Ulrich},
	booktitle={CVPR},
	year={2018}
}

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Weiyue Wang, Qiangui Huang, Suya You, Chao Yang and Ulrich Neumann International Conference on Computer Vision (ICCV), 2017 paper | bibtex

@inproceedings{wang2017shapeinpainting,
	title={Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks},
	author={Wang, Weiyue and Huang, Qiangui and You, Suya and Yang, Chao and Neumann, Ulrich},
	booktitle={ICCV},
	year={2017}
}

Self-Paced Cross-Modality Transfer Learning for Efficient Road Segmentation

Weiyue Wang, Naiyan Wang, Xiaomin Wu, Suya You and Ulrich Neumann International Conference on Robotics and Automation (ICRA), 2017

paper | bibtex

@inproceedings{wang2017selfpaced,
	title={Self-Paced Cross-Modality Transfer Learning for Efficient Road Segmentation},
	author={Wang, Weiyue and Wang, Naiyan and Wu, Xiaomin and You, Suya and Yang, Chao and Neumann, Ulrich},
	booktitle={ICRA},
	year={2017}
}

Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning

Qiangui Huang, Weiyue Wang, Kevin Zhou, Suya You and Ulrich Neumann arXiv preprint, 2016

paper | bibtex

@article{huang2016scenelabeling,
	title={Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning},
	author={Huang, Qiangui and Wang, Weiyue and Zhou, Kevin and You, Suya and Neumann, Ulrich},
	journal={arXiv preprint arXiv:1611.07485},
	year={2016}
}

Undergrad Works

A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes

Weiyao Lin, Yang Mi, Weiyue Wang, Jianxin Wu, and Jingdong Wang IEEE Transaction on Image Processing (TIP), 2016

paper | bibtex

@article{lin2016tip,
	title={A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes},
	author={Lin, Weiyao and Mi, Yang and Wang, Weiyue and Wu, Jianxin and Wang, Jingdong},
	journal={IEEE Transaction on Image Processing (TIP)},
	year={2016}
}

Finding Coherent Motions and Understanding Crowd Scenes: a Diffusion and Clustering-based Approach

Weiyao Lin, Yang Mi and Weiyue Wang IEEE Conference on Computer Vision and Pattern Recognition Scene Understanding Workshop (CVPR SUNw), 2015

paper

Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach

Weiyue Wang, Weiyao Lin, Yuanzhe Chen, Jianxin Wu, Jingdong Wang, and Bin Sheng European Conference on Computer Vision (ECCV), 2014

paper | bibtex

@inproceedings{wang2017coherentmotions,
	title={Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach},
	author={Wang, Weiyue and Lin, Weiyao and Chen, Yuanzhe and Wu, Jianxin and Wang, Jingdong and Sheng, Bin},
	booktitle={ECCV},
	year={2014}
}

Experience

Internships:
Adobe, Summer 2018, San Jose
TuSimple, Summer 2017, San Diego
TuSimple, Summer 2016, Beijing

Teaching:
USC CSCI-677 Advanced Computer Vision, Fall 2018
USC CSCI-585 Database System, Spring 2017

Reviewer:
ICCV19, CVPR19, TPAMI, CVPR18, ICRA18, IROS18, ACCV18, CVIU,
ISPRS Journal of Photogrammetry

Weiyue Wang

Ph.D. Student in Computer Science

University of Southern California

CV

GitHub

Google Scholar

About Me

Publications

Ph.D. Works

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

3DN: 3D Deformation Network

Depth-aware CNN for RGB-D Segmentation

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Recurrent Slice Networks for 3D Segmentation on Point Clouds

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Self-Paced Cross-Modality Transfer Learning for Efficient Road Segmentation

Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning

Undergrad Works

A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes

Finding Coherent Motions and Understanding Crowd Scenes: a Diffusion and Clustering-based Approach

Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach

Experience

Misc

Weiyue Wang

Ph.D. Student in Computer Science

University of Southern California

CV GitHub Google Scholar

About Me

Publications

Ph.D. Works

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

3DN: 3D Deformation Network

Depth-aware CNN for RGB-D Segmentation

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Recurrent Slice Networks for 3D Segmentation on Point Clouds

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Self-Paced Cross-Modality Transfer Learning for Efficient Road Segmentation

Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning

Undergrad Works

A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes

Finding Coherent Motions and Understanding Crowd Scenes: a Diffusion and Clustering-based Approach

Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach

Experience

Misc

CV

GitHub

Google Scholar