Kangxue Yin

Senior Research Scientist, NVIDIA

kangxue.yin [at] gmail [dot] com


I am a senior research scientist at NVIDIA's Toronto AI lab. I work on computer graphics, vision, 3D deep learning and generative AI, and their applications in 3D content creation, 3D reconstruction and virtual world simulation. I received my Ph.D. degree from Simon Fraser University(SFU) in 2020 where I worked in the GrUVi lab under the supervision of Prof. Hao (Richard) Zhang. I also worked with Prof. Hui Huang and Prof. Daniel Cohen-Or who were on my supervisory committee as well. Prior to starting my Ph.D., I worked at Shenzhen Institutes of Advanced Technology (SIAT.CAS). I received my B.Eng. degree from Chang'an University (Xi'an, China) in 2012.


TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models.
Tianshi Cao , Karsten Kreis , Sanja Fidler , Nicholas Sharp, Kangxue Yin.
ICCV 2023 (oral)
[paper][project page]

Flexible Isosurface Extraction for Gradient-Based Mesh Optimization.
Tianchang Shen, Jacob Munkberg, Jon Hasselgren, Kangxue Yin, Zian Wang, Wenzheng Chen, Zan Gojcic, Sanja Fidler, Nicholas Sharp, Jun Gao.
ACM Transactions on Graphics 42(4)(Special Issue of SIGGRAPH 2023 )
[paper][project page]

NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models.
Seung Wook Kim*, Bradley Brown*, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, Sanja Fidler
CVPR, 2023
[paper][project page]

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images.
Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, Sanja Fidler
NeurIPS, 2022
[paper][project page]
MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation.
Gopal Sharma, Kangxue Yin, Subhransu Maji, Evangelos Kalogerakis, Or Litany, Sanja Fidler
ECCV, 2022
[paper][project page]
AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis.
Zhiqin Chen, Kangxue Yin, Sanja Fidler
CVPR, 2022
[paper][project page]
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis.
Tianchang Shen, Jun Gao, Kangxue Yin, Ming-Yu Liu, Sanja Fidler
NeurIPS, 2021
[paper][project page]

3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations.
Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, Sanja Fidler
ICCV 2021 (oral)
[paper][project page]

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes.
Towaki Takikawa*, Joey Litalien*, Kangxue Yin, Karsten Kreis, Charles Loop, Derek Nowrouzezahrai, Alec Jacobson, Morgan McGuire, Sanja Fidler
CVPR 2021 (oral)
[paper][project page]
DatasetGAN: Efficient labeled data factory with minimal human effort.
Yuxuan Zhang*, Huan Ling*, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler
CVPR 2021 (oral)
[paper][project page]
COALESCE: Component Assembly by Learning to Synthesize Connections.
Kangxue Yin, Zhiqin Chen, Siddhartha Chaudhuri, Matthew Fisher, Vladimir Kim, Hao Zhang.
3DV 2020 (oral)
[paper][video][data and code]
FAME: 3D Shape Generation via Functionality-Aware Model Evolution.
Yanran Guan, Han Liu, Kun Liu, Kangxue Yin, Ruizhen Hu, Oliver van Kaick, Yan Zhang, Ersin Yumer, Nathan Carr, Radomir Mech, and Hao Zhang.
IEEE Transactions on Visualization and Computer Graphics(TVCG), 2020.
LOGAN: Unpaired Shape Transform in Latent Overcomplete Space.
Kangxue Yin, Zhiqin Chen, Hui Huang, Daniel Cohen-Or, Hao Zhang.
ACM Transactions on Graphics 38(6)(Special Issue of SIGGRAPH ASIA 2019 ).
[paper] [supp.] [slides] [project page] [data] [code]
[selected by SIGGRAPH ASIA 2019 as one of six papers featured for press release]
BAE-NET: Branched Autoencoder for Shape Co-Segmentation.
Zhiqin Chen, Kangxue Yin, Matthew Fisher, Siddhartha Chaudhuri, Hao Zhang.
Proc. of ICCV 2019
[paper][supp.][data + code]
P2P-NET: Bidirectional Point Displacement Net for Shape Transform.
Kangxue Yin, Hui Huang, Daniel Cohen-Or, Hao Zhang.
ACM Transactions on Graphics 37(4)(Special Issue of SIGGRAPH 2018 )
[paper][project page][slides][fast-forward][data(hdf5)][data(raw)][code]
A Sampling Approach to Generating Closely Interacting 3D Pose-pairs from 2D Annotations.
Kangxue Yin, Hui Huang, Edmond S. L. Ho, Hao Wang, Taku Komura, Daniel Cohen-Or, Hao Zhang.
IEEE Transactions on Visualization and Computer Graphics(TVCG), 2018.
Full 3D Plant Reconstruction via Intrusive Acquisition.
Kangxue Yin, Hui Huang, Pinxin Long, Alex Gaissinski, Minglun Gong, Andrei Sharf.
Computer Graphics Forum 35(1), 2016.
[paper][project page][data]

Generalized Cylinder Decomposition.
Yang Zhou, Kangxue Yin, Hui Huang, Hao Zhang, Minglun Gong, Daniel Cohen-Or.
ACM Transactions on Graphics 34(6)(Special Issue of SIGGRAPH ASIA 2015 ).
[paper][video][code + data + page]

Morfit: Interactive Surface Reconstruction from Incomplete Point Clouds with Curve-Driven Topology and Geometry Control.
Kangxue Yin, Hui Huang, Hao Zhang, Minglun Gong, Daniel Cohen-or, Baoquan Chen.
ACM Transactions on Graphics 33(6)(Special Issue of SIGGRAPH ASIA 2014 ).
[paper][project page][video][slides][code + data]
"Mind the Gap": Tele-Registration for Structure-Driven Image Completion.
Hui Huang, Kangxue Yin, Minglun Gong, Dani Lischinski, Daniel Cohen-Or, Uri Ascher, Baoquan Chen.
ACM Transactions on Graphics 32(6)(Special Issue of SIGGRAPH ASIA 2013 ).
[paper][slides][core code + data]