Search results
Jun Gao is a 3D computer vision and graphics expert, working on 3D generative AI models for realistic and diverse 3D content creation. He is affiliated with the University of Toronto and the Vector Institute, and will join the University of Michigan in 2025.
- K. Jun Gao
K. Jun Gao. As of 4 July 2023. I’m a research student and...
- K. Jun Gao
Articles 1–20. University of Toronto, NVIDIA - Cited by 3,951 - Computer Vision - Machine Learning.
Jun Gao. jungao@cs.toronto.edu ⋄ Homepage ⋄ Google Scholar ⋄ (+1) 437-985-2877 I am interested in computer vision, computer graphics and machine learning. I develop 3D generative AI models to create realistic, high-quality and diverse 3D content for reconstructing, generating and simulating 3D worlds.
- 100KB
- 3
REAM♯: An enhancement approach to reference-based evaluation metrics for open-domain dialog generation. J Gao, W Bi, R Xu, S Shi. ACL'2021 (Findings) , 2021. 9. 2021. Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset.
Jul 4, 2023 · K. Jun Gao. As of 4 July 2023. I’m a research student and fourth-year undergraduate at the University of Toronto. I am pursuing a degree in computer science, bioinformatics and computational biology, with a math minor and focus in theoretical CS.
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis. Your browser does not support the video tag. We introduce DMTet, a deep 3D conditional generative model that can synthesize high-resolution 3D shapes using simple user guides such as coarse voxels or noisy point cloud.
Sep 22, 2022 · Jun Gao and co-authors propose GET3D, a method to synthesize high-quality 3D textured meshes from 2D images. GET3D bridges differentiable surface modeling, rendering and 2D generative networks, and achieves significant improvements over previous methods.
