Yue Wang

I am a Research Scientist at NVIDIA Research Autonomous Vehicle Research Group, working with Marco Pavone. I graduated from MIT EECS in 2022, advised by Justin Solomon at Geometric Data Processing Group. I was also fortunate to collaborate with Michael Bronstein and Phillip Isola. Previously, I was a master student at University of California, San Diego. Prior to that, I received my BEng in Computer Science from Zhejiang University. I’ve received the Nvidia Fellowship (2020-2021) and the MIT EECS William A. Martin Master’s Thesis Award (2021).

My research lies in the intersection of computer vision, computer graphics, and robotics. My goal is to use machine learning to enable robot intelligence with minimal human supervision. I study how to design 3D learning systems which leverage geometry, appearance, and any other cues that are naturally available in sensory inputs. I am also broadly interested in eclectic applications on top of these systems.

Topics I currently focus on include:

Neural fields for robotics and autonomous driving: FreeNeRF
Generative AI for 3D perception
Geometry-inspired self-supervised learning

Past topics:

Geometric deep learning: DGCNN, DCP, PRNet, Object DGCNN, PointGrow
3D perception for robotics and autonomous driving: PillarOD, Object DGCNN, DETR3D, HDMapNet
2D/3D self-supervised learning and few-shot learning: FeatureDecor, RFS, STAR, RepLearnPoint

We are organizing “Vision-Centric Autonomous Driving Workshop” at CVPR2023. Submit your recent papers, and participate in our novel challenges!

news

Feb 27, 2023	Four papers (few-shot neural rendering, representation learning for point clouds, end-to-end prediction for AV, and map learning) accepted to CVPR 2023!
Dec 30, 2022	Our workshop proposal “Data-Driven Visual Autonomous Driving (DDVAD)” has been accepted to CVPR2023. See you in Vancouver!
Sep 11, 2022	Two papers accepted to CORL 2022.
Sep 6, 2022	I joined Nvidia Research as a Research Scientist.

selected publications

CVPR

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

Jiawei Yang, Marco Pavone, and Yue Wang

In The Conference on Computer Vision and Pattern Recognition 2023

Bib PDF Code Website

@inproceedings{yang2023freenerf,
  title = {FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization},
  author = {Yang, Jiawei and Pavone, Marco and Wang, Yue},
  year = {2023},
  booktitle = {The Conference on Computer Vision and Pattern Recognition},
}

CORL

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries

Yue Wang, Vitor Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, and Justin M. Solomon

In The Conference on Robot Learning 2021

Bib PDF Code

@inproceedings{detr3d,
  title = {DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries},
  author = {Wang, Yue and Guizilini, Vitor and Zhang, Tianyuan and Wang, Yilun and Zhao, Hang and and Solomon, Justin M.},
  booktitle = {The Conference on Robot Learning},
  year = {2021},
}

ECCV

Rethinking few-shot image classification: a good embedding is all you need?

Yonglong Tian*, Yue Wang*, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola

In The European Conference on Computer Vision 2020

Bib PDF Code

@inproceedings{tian2020rethink,
  title = {Rethinking few-shot image classification: a good embedding is all you need?},
  author = {Tian*, Yonglong and Wang*, Yue and Krishnan, Dilip and Tenenbaum, Joshua B and Isola, Phillip},
  booktitle = {The European Conference on Computer Vision},
  year = {2020},
}

NeurIPS

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

Yue Wang, and Justin M. Solomon

In Conference on Neural Information Processing Systems 2019

Bib PDF Code

@inproceedings{Wang2019PRNet,
  title = {PRNet: Self-Supervised Learning for Partial-to-Partial Registration},
  author = {Wang, Yue and Solomon, Justin M.},
  booktitle = {Conference on Neural Information Processing Systems},
  year = {2019},
}

ICCV

Deep Closest Point: Learning Representations for Point Cloud Registration

Yue Wang, and Justin M. Solomon

In The International Conference on Computer Vision 2019

Bib PDF Code

@inproceedings{Wang2019DeepCP,
  title = {Deep Closest Point: Learning Representations for Point Cloud Registration},
  author = {Wang, Yue and Solomon, Justin M.},
  booktitle = {The International Conference on Computer Vision},
  year = {2019},
}

TOG

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon

ACM Transactions on Graphics 2019

Bib PDF Code

@article{Wang2018DynamicGC,
  title = {Dynamic Graph CNN for Learning on Point Clouds},
  author = {Wang, Yue and Sun, Yongbin and Liu, Ziwei and Sarma, Sanjay E. and Bronstein, Michael M. and Solomon, Justin M.},
  journal = {ACM Transactions on Graphics},
  year = {2019},
  volume = {38},
  issue = {5},
  page = {146},
}