Hanxiao Jiang(Shawn) | 蒋含啸
为天地立心，为生民立命。 为往圣继绝学，为万世开太平。 --- 《横渠语录》
To ordain conscience for Heaven and Earth. To secure life and fortune for the people. To continue lost teachings for past sages. To establish peace for all future generations.
I'm a theis-based master student of computer science at Simon Fraser University, instructed by professor Angel Xuan Chang. Prior to this, I received my Bachelor of Engineer & Bachelor of Science from Zhejiang University and Simon Fraser University. Currently I am also a research assistant in SFU Gruiv Group working with professor Angel Xuan Chang and professor Manolis Savva at Simon Fraser University. My research interests are 3D vision and robotics vision.
- June, 2020 - Got SFU Alumni Scholarship, Simon Fraser University.
- May, 2020 - Got Undergraduate Open Scholarship for 2020 Summer, Simon Fraser University.
- May, 2020 - Got President's & Dean's Honour Roll for 2020 Spring, Simon Fraser University.
- March, 2020 - I will be a master student in Simon Fraser University , instructed by Prof. Angel Xuan Chang.
- February, 2020 - One paper accepted at CVPR 2020.
- February, 2020 - Got Fortinet Undergraduate Scholarship in Computing Science and Engineering, Simon Fraser University.
SAPIEN: A SimulAted Part-based Interactive ENvironmentFanbo Xiang*, Yuzhe Qin*, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao Jiang, Yifu Yuan, He Wang, Li Yi, Angel X.Chang, Leonidas J. Guibas and Hao Su
CVPR 2020, Oral Presentation
We propose a realistic and physics-rich simulation environment hosting large-scale 3D articulated objects from ShapeNet and PartNet. Our PartNet-Mobility dataset contains 14,068 articulated parts with part motion information for 2,346 object models from 46 common indoor object categories. SAPIEN enables various robotic vision and interaction tasks that require detailed part-level understanding.[Paper] [Project] [Demo]
Evaluating Colour Constancy on the new MIST dataset of Multi-Illuminant ScenesXiangpeng Hao, Brian Funt, Hanxiao Jiang
CIC 2019, Oral Presentation
A new image test set of synthetically generated, full-spectrum images with pixelwise ground truth has been developed to aid in the evaluation of illumination estimation methods for colour constancy. The performance of 9 illumination methods is reported for this dataset along and compared to the optimal single-illuminant estimate. None of the methods specifically designed to handle multi-illuminant scenes is found to perform any better than the optimal single-illuminant case based on completely uniform illumination.[Paper]