Welcome to Rui Ma's homepage
 
About me

[Updated: 2021] This page is out of date, please visit my new website

My name is Rui Ma (马锐). I'm working as a Research Scientist at AltumView Systems Inc, Canada. My previous and current research interests include computer graphics, computer vision, robotics and natural language processing. I'm motivated to learn, develop and apply state-of-the-art research into practical industrial applicaitons and products.

I recieved my Ph.D. in Computer Science in 2018, from School of Computing Science, Simon Fraser University, Canada. At SFU, I worked in the GrUVi Lab under the supervision of Prof. Hao (Richard) Zhang for my PhD study. Before that, I obtained my M.Sc. and B.Sc. both in Computational Mathmatics from Jilin University, China.

Email: ruim@sfu.ca            LinkedIn            Google Scholar

Publication
Rui Ma, Akshay Gadi Patil, Matthew Fisher, Manyi Li, Sören Pirk, Binh-Son Hua,
Sai-Kit Yeung, Xin Tong, Leonidas Guibas, Hao Zhang.
"Language-Driven Synthesis of 3D Scenes from Scene Databases".
ACM Transactions on Graphics (SIGGRAPH Asia 2018), 37(6).

We introduce a novel framework for using natural language to generate and edit 3D indoor scenes, harnessing scene semantics and text-scene grounding knowledge learned from large annotated 3D scene databases.

Rui Ma, Honghua Li, Changqing Zou, Zicheng Liao, Xin Tong and Hao Zhang.
"Action-Driven 3D Indoor Scene Evolution".
ACM Transactions on Graphics (SIGGRAPH Asia 2016), 35(6).

We introduce a framework for action-driven evolution of 3D indoor scenes, where the goal is to simulate how scenes are altered by human actions, and specifically, by object placements necessitated by the actions.

Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or and Hui Huang.
"Organizing Heterogeneous Scene Collection through Contextual Focal Points".
ACM Transactions on Graphics (SIGGRAPH 2014), 33(4).

We introduce focal points for characterizing, comparing, and organizing collections of complex and heterogeneous data and apply the concepts and algorithms developed to collections of 3D indoor scenes.

Ibraheem Alhashim, Honghua Li, Kai Xu, Junjie Cao, Rui Ma and Hao Zhang.
"Topology-Varying 3D Shape Creation via Structural Blending".
ACM Transactions on Graphics (SIGGRAPH 2014), 33(4).

We introduce an algorithm for generating novel 3D models via topology-varying shape blending. Given two shapes with different topology, our method blends them topologically and geometrically, producing continuous series of in-betweens representing new creations.

Thesis
Rui Ma
"Sub-Scene Level Analysis and Synthesis of 3D Indoor Scenes".
SFU Ph.D. Thesis, 2017.

In this thesis, we address the problems of data-driven 3D indoor scene analysis and synthesis via sub-scene level processing. The goal is to improve the understanding of scene structures through sub-scene level analysis and develop efficient systems to create complex scenes by manipulating sub-scenes instead of individual objects.

Report

Rui Ma
"Analysis and Modeling of 3D Indoor Scenes".
SFU Depth Examination Report, 2017 Summer.

This report surveys the recent research progress in graphics on geometry, structure and semantic analysis of 3D indoor data and different modeling techniques for creating plausible and realistic indoor scenes.

Patent

Rui Ma, Chao Shen, Yu Gao, Ye Lu, Minghua Chen, Jie Liang and Jianbing Wu
AltumView Systems Inc., Canada
"Obstacle Avoidance System based on Embedded Stereo Vision for Unmanned Aerial Vehicles".
US Patent US10776939, Granted, 2020

Him Wai Ng, Xing Wang, Yu Gao, Rui Ma and Ye Lu
AltumView Systems Inc., Canada
"Enhanced Face-Detection and Face-Tracking for Resource-Limited Embedded Vision Systems".
Published December 2018.
US Patent US10691925, Granted, 2020

Yu Gao, Xing Wang, Eric Honsch, Rui Ma, Chao Shen, Minghua Chen,
Ye Lu, Jie Liang and Jianbing Wu
AltumView Systems Inc., Canada
"High-Performance Visual Object Tracking for Embedded Vision Systems".
Published December 2018.
US Patent US20190304105, Published, 2019