Weiwei Sun

Applied Scientist

Amazon Science, Vancouver, Canada.
Email: weiwei.sun3 [at] gmail.com


Biography

I am an Applied Scientist at Amazon. I earned my Ph.D. in Computer Science, University of British Columbia (UBC), where I was co-advised by Dr. Kwang Moo Yi and Dr. Andrea Tagliasacchi. Prior to that, I completed a master's degree in Digital Imaging System at University of Calgary and a bachelor's degree in Geographic Information System (GIS) at Wuhan University.

I have been also very fortunate to receive advices during my Ph.D. studies/internships from Geoffrey Hinton, Eduard Trulls, Soroosh Yazdani, Sanja Fidler, Zan Gojcic, Jun Gao, Amin Banitalebi. They inspired me a lot on my research.

My research lies at the intersection of 3D computer vision and graphics, including areas such as visual geometry, 3D reconstruction, point clouds, neural rendering, and more. My goal is to equip machines with the ability to perceive, simulate, and interact with 3D environments by training deep models. I am particularly enthusiastic about solving real-world problems using these models.

News

[Show more]

Selected Publications [Google Scholar]

* below indicates equal contribution; Representative works are highlighted.
Densify Your Labels: Unsupervised Clustering with Bipartite Matching for Weakly Supervised Point Cloud Segmentation -- ArXiv'24
Shaobo Xia, Jun Yue, Kacper Kania, Leyuan Fang, Andrea Tagliasacchi, Kwang Moo Yi, Weiwei Sun
I'm the advisor of this project.
ArXiv (Preprint)
[Paper, Project]
NoKSR: Kernel-free Neural Surface Reconstruction via Point Cloud Serialization -- 3DV'25
Zhen Li*, Weiwei Sun*, Shrisudhan Govindarajan, Shaobo Xia, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
IEEE International Conference on 3D Vision
[Paper, Project]
3D Gaussian Splatting as Markov Chain Monte Carlo -- NeurIPS'24 (Spotlight)
Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Jeff Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi.
Neural Information Processing Systems (NeurIPS)
[Paper, Project]
Lagrangian Hashing for Compressed Neural Field Representation -- ECCV'24
Shrisudhan Govindarajan, Zeno Sambugaro, Ahan Shabhanov, Towaki Takikawa, Weiwei Sun, Daniel Rebain, Nicola Conci, Kwang Moo Yi, Andrea Tagliasacchi
Proceedings of the European Conference on Computer Vision (ECCV)
[Paper, Project]
PointNeRF++: A multi-scale, point-based Neural Radiance Field -- ECCV'24
Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi
Proceedings of the European Conference on Computer Vision (ECCV)
[Paper, Project]
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds -- WACV'23
Weiwei Sun, Daniel Rebain, Renjie Liao, Vladimir Tankovich, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi
Winter Applications of Computer Vision (WACV)
[Paper, Project]
TUSK: Task-agnostic Unsupervised Keypoints -- NeurIPS'22
Yuhe Jin, Weiwei Sun, Jan Hosang, Eduard Trulls, Kwang Moo Yi
Neural Information Processing Systems (NeurIPS)
[ArXiv, Paper]
Canonical Capsules: Self-supervised Capsules in Canonical Pose -- NeurIPS'21
Weiwei Sun*, Andrea Tagliasacchi*, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi
Neural Information Processing Systems (NeurIPS)
[Paper, Project, Code]
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning -- CVPR'20
Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
[Paper, Code, Project, ]
Optimizing Through Learned Errors for Accurate Sports Field Registration -- WACV'20
Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles, Weiwei Sun, Mehrsan Javan, Kwang Moo Yi
Winter Conference on Applications of Computer Vision (WACV)
[Paper, Code]
Linearized Multi-Sampling for Differentiable Image Transformation -- ICCV'19 (Oral)
Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi
Proceedings of the International Conference on Computer Vision(ICCV)
[Paper, Code]
Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM -- IEEE GRSL (Top cited)
Weiwei Sun, Ruisheng Wang
IEEE Geoscience and Remote Sensing Letters
[Paper]

Experience

Professional Activities

Selected Honors & Awards