Jingwei Huang


Research interests

My research interests are computer graphics, computer vision, virtual reality and geometry processing. After involving in projects from different areas in graphics and vision, I determined to focus on RGB-D SLAM and Real-time reconstruction in order to produce read-to-use high-quality scanning geometry. My ultimate goal is to effectively recognize the scanning data in a higher level. Towards the goal, I believe that it is essential to bridge two fields --- computer vision and computer graphics, where the former focuses on visual SLAM and the latter on geometrical data analysis and synthesis. To achieve the goal of producing high-quality geometry, we need high-quality texture and clean geometry. I contributed to the 3D geometry texture synthesis component of the "unsupervised texture synthesis" project. Now, I am working on the "3DLite" system to get clean geometry with good planar abstraction.

Recent publications

(All the publications are available on the personal page linked above)
Huang J, Chen Z, Ceylan D, et al. 6-DOF VR videos with a single 360-camera[C]//Virtual Reality (VR), 2017 IEEE. IEEE, 2017: 37-44.   
Wang T Y, Su H, Huang Q, et al. Unsupervised texture transfer from images to model collections[J]. ACM Trans. Graphics (TOG), 2016, 35(6): 177.   
Quigley E, Yu Y, Huang J, et al. Real-time Interactive Tree Animation[J]. IEEE Transactions on Visualization and Computer Graphics, 2017.   
Huang J, Chen H, Wang B, et al. Automatic thumbnail generation based on visual representativeness and foreground recognizability[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 253-261.   
Huang J, Wang B, Wang W, et al. A surface approximation method for image and video correspondences[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5100-5113.