I am a second year PhD student at Department of Computer Science, Cornell University, advised by Prof. Serge Belongie. My research interests lie in solving computer vision and computer graphics problems with machine learning. See my personal page for more details.
2021 |
| Hao, Zekun; Mallya, Arun; Belongie, Serge; Liu, Ming-Yu GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds International Conference on Computer Vision (ICCV), Virtual, 2021. (Links | BibTeX) @conference{Hao2021,
title = {GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds},
author = {Zekun Hao and Arun Mallya and Serge Belongie and Ming-Yu Liu},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2021/08/08075.pdf},
year = {2021},
date = {2021-10-11},
booktitle = {International Conference on Computer Vision (ICCV)},
address = {Virtual},
keywords = {}
}
|
2020 |
| Cai*, Ruojin; Yang*, Guandao; Averbuch-Elor, Hadar; Hao, Zekun; Belongie, Serge; Snavely, Noah; Hariharan, Bharath Learning Gradient Fields for Shape Generation European Conference on Computer Vision (ECCV), Glasgow, Scotland, 2020, (Spotlight, *Equal Contribution). (Links | BibTeX) @conference{Cai2020,
title = {Learning Gradient Fields for Shape Generation},
author = {Ruojin Cai* and Guandao Yang* and Hadar Averbuch-Elor and Zekun Hao and Serge Belongie and Noah Snavely and Bharath Hariharan},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2020/08/ShapeGF-1.pdf},
year = {2020},
date = {2020-08-24},
booktitle = {European Conference on Computer Vision (ECCV)},
journal = {European Conference on Computer Vision (ECCV)},
address = {Glasgow, Scotland},
note = {Spotlight, *Equal Contribution},
keywords = {}
}
|
| Hao, Zekun; Averbuch-Elor, Hadar; Snavely, Noah; Belongie, Serge DualSDF: Semantic Shape Manipulation using a Two-Level Representation Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 2020. (Abstract | Links | BibTeX) @conference{Hao2020,
title = {DualSDF: Semantic Shape Manipulation using a Two-Level Representation},
author = {Zekun Hao and Hadar Averbuch-Elor and Noah Snavely and Serge Belongie },
url = {https://vision.cornell.edu/se3/wp-content/uploads/2020/04/DualSDF_zekun_cvpr20.pdf},
year = {2020},
date = {2020-06-15},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
address = {Seattle, WA},
abstract = {We are seeing a Cambrian explosion of 3D shape representations for use in machine learning. Some representations seek high expressive power in capturing high-resolution detail. Other approaches seek to represent shapes as compositions of simple parts, which are intuitive for people to understand and easy to edit and manipulate. However, it is difficult to achieve both fidelity and interpretability in the same representation. We propose DualSDF, a representation expressing shapes at two levels of granularity, one capturing fine details and the other representing an abstracted proxy shape using simple and semantically consistent shape primitives. To achieve a tight coupling between the two representations, we use a variational objective over a shared latent space. Our two-level model gives rise to a new shape manipulation technique in which a user can interactively manipulate the coarse proxy shape and see the changes instantly mirrored in the high-resolution shape. Moreover, our model actively augments and guides the manipulation towards producing semantically meaningful shapes, making complex manipulations possible with minimal user input.},
keywords = {}
}
We are seeing a Cambrian explosion of 3D shape representations for use in machine learning. Some representations seek high expressive power in capturing high-resolution detail. Other approaches seek to represent shapes as compositions of simple parts, which are intuitive for people to understand and easy to edit and manipulate. However, it is difficult to achieve both fidelity and interpretability in the same representation. We propose DualSDF, a representation expressing shapes at two levels of granularity, one capturing fine details and the other representing an abstracted proxy shape using simple and semantically consistent shape primitives. To achieve a tight coupling between the two representations, we use a variational objective over a shared latent space. Our two-level model gives rise to a new shape manipulation technique in which a user can interactively manipulate the coarse proxy shape and see the changes instantly mirrored in the high-resolution shape. Moreover, our model actively augments and guides the manipulation towards producing semantically meaningful shapes, making complex manipulations possible with minimal user input.
|
2019 |
| Yang*, Guandao; Huang*, Xun; Hao, Zekun; Liu, Ming-Yu; Belongie, Serge; Hariharan, Bharath PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows International Conference on Computer Vision (ICCV), Seoul, Korea, 2019, (Oral, *Equal Contribution). (Abstract | Links | BibTeX) @conference{YangHuang2019,
title = {PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows},
author = {Guandao Yang* and Xun Huang* and Zekun Hao and Ming-Yu Liu and Serge Belongie and Bharath Hariharan },
url = {https://vision.cornell.edu/se3/wp-content/uploads/2019/09/1906.12320.pdf},
year = {2019},
date = {2019-10-27},
booktitle = {International Conference on Computer Vision (ICCV)},
address = {Seoul, Korea},
abstract = {https://arxiv.org/abs/1906.12320
https://www.guandaoyang.com/PointFlow},
note = {Oral, *Equal Contribution},
keywords = {}
}
https://arxiv.org/abs/1906.12320
https://www.guandaoyang.com/PointFlow
|
2018 |
| Hao, Zekun; Huang, Xun; Belongie, Serge Controllable Video Generation with Sparse Trajectories Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, 2018. (Links | BibTeX) @conference{Hao2018,
title = {Controllable Video Generation with Sparse Trajectories},
author = {Zekun Hao and Xun Huang and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2018/03/1575.pdf},
year = {2018},
date = {2018-06-18},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
address = {Salt Lake City, UT},
keywords = {}
}
|