Fanglue Zhang
Teaching in 2018
Course Lecturer
Course Lecturer
After earning my doctoral degree working on structure-based image analysis and editing at the Visual Media Lab at Tsinghua in 2015, I continued working as a Post-Doctoral researcher and collaborating on research projects with industry, where my research focus was mainly on the intelligent image and video editing and enhancement. In 2017, my research was recognised by the Faculty of Engineering and Computer Graphics group at Victoria University of Wellington; I was appointed to the lecturer position. I incorporate my background in Virtual Reality into the CG group’s research by solving the problems of improving the visual quality of 360 degree videos. I am also working on a SfTI Robotics project, where I focus on providing efficient deep learning method for RGB-D object recognition and segmentation.
I have contributed to intelligent image/video processing and editing, with my work being published in the highest quality journals and conferences in Computer Graphics, including SIGGRAPH/SIGGRAPH Asia, IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Multimedia, and IEEE Transactions on Image Processing. My work on repeated structure and shape analysis, library-driven editing, and aesthetic-based composition adjustment are all state-of-the-art tools on image and video editing tasks.
Research Interests
Computer graphics, computational photography, deep learning, machine learning, image and video analysis and editing
Publications
--Detecting and Removing Visual Distractors for Video Aesthetic Enhancement,
Fang-Lue Zhang, Xian Wu, Rui-Long Li, Zhao-Heng Zheng, Jue Wang, Shi-Min Hu,
IEEE Transactions on Multimedia, 2018, to appear
2017:
--PlenoPatch: Patch-based Plenoptic Image Manipulation,
Fang-Lue Zhang, JueWang, Eli Shechtman, Zi-Ye Zhou, Jia-Xin Shi and Shi-Min Hu,
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017
--Image-based clothes changing system. Zhao-Heng Zheng, Hao-Tian Zhang,
Fang-Lue Zhang, Tai-Jiang Mu. Computational Visual Media, 1-11, 2017
--Robust tracking-by-detection using a selection and completion mechanism. Ruochen Fan,
Fang-Lue Zhang, Min Zhang, Ralph R. Martin. Computational Visual Media, 1-10, 2017
--High-speed video generation with an event camera. Han-Chao Liu,
Fang-Lue Zhang, David Marshall, L Shi, Shi-Min Hu. The Visual Computer, 2017
--A survey of the state-of-the-art in patch-based synthesis. Connelly Barnes,
Fang-Lue Zhang. Computational Visual Media, 1-18, 2017
2016:
--Robust Background Identification for Dynamic Video Editing,
Fang-Lue Zhang, Xian Wu, Jue Wang, Hao-Tian Zhang, Shi-Min Hu.
ACM Transactions on Graphics (SIGGRAPH Asia),
2016
2015:
--Simultaneous Camera Path Optimization and Distraction Removal for Improving Amateur Video.
Fang-Lue Zhang, Jue Wang, Han Zhao, Ralph R. Martin, Shi-Min Hu.
IEEE Transactions on Image Processing (TIP), 2015
--PatchTable: Efficient Patch Queries for Large Datasets and Applications. Connelly Barnes,
Fang-Lue Zhang, Liming Lou, Xian Wu, Shi-Min Hu.
ACM Transactions on Graphics (SIGGRAPH), 2015
2013:
--PatchNet: A Patch-based Image Representation for Interactive Library-driven Image Editing. Shi-Min Hu,
Fang-Lue Zhang, Miao Wang, Ralph R. Martin and Jue Wang.
ACM Transactions on Graphics (SIGGRAPH Asia), 2013
--Aesthetic Image Enhancement by Dependence-Aware Object Re-composition.
Fang-Lue Zhang, Miao Wang, Shi-Min Hu.
IEEE Transactions on Multimedia (TMM), 2013
2012:
--ImageAdmixture: Putting Together Dissimilar Objects from Groups.
Fang-Lue Zhang, Ming-Ming Cheng, Jiaya Jia, Shi-Min Hu.
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2012
--Data-Driven Object Manipulation in Images. Chen Goldberg, Tao Chen,
Fang-Lue Zhang, Ariel Shamir, Shi-Min Hu. Computer Graphics Forum (Eurographics), 2012
2010:
--RepFinder: Finding Approximately Repeated Scene Elements for Image Editing. Ming-Ming Cheng,
Fang-Lue Zhang, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu.
ACM Transactions on Graphics (SIGGRAPH 2010), 30(4), 2010
Refer to Google Scholar for all my publications 