Visual Computing

Addressing the world's more pressing issues such as environmental sustainability and cultural heritage preservation increasingly relies on diverse visual applications running on emerging platforms such as AR/VR headsets, autonomous machines, and smart sensor nodes. In real-time and using low power, visual computing systems must generate visual data for human to consume, immersively, or interpret visual data to provide personalized services, intelligently.

Today's computer systems and architecture are not ready for the visual computing on the horizon. We explore the road that might get us there. We advocate both horizontal innovation, by co-designing different domains that are conventionally designed and optimized in isolation (e.g., vision, imaging, graphics, video, optics), and vertical innovation, by rethinking the systems stack for 3D visual computing in point clouds.

Recent Publications

Continuous Vision

ASV: Accelerated Stereo Vision System
[MICRO 2019] Yu Feng, Paul Whatmough, Yuhao Zhu
SVSoC: Speculative Vision Systems-on-a-Chip
[CAL 2019] Yiming Gan, Yuxian Qiu, Jingwen Leng, Yuhao Zhu
Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision
[ISCA 2018] Yuhao Zhu, Anand Samajdar, Matthew Mattina, Paul Whatmough

Point Cloud

Tigris: Architecture and Algorithms for 3D Perception in Point Clouds
[MICRO 2019] Tiancheng Xu*, Boyuan Tian*, Yuhao Zhu (* Co-primary authors)

Virtual Reality/360º Video

Energy-Efficient 360-Degree Video Rendering on FPGA via Algorithm-Architecture Co-Design
[FPGA 2020] Qiuyue Sun, Amir Taherin, Yawo Siatitse, Yuhao Zhu
Energy-Efficient Video Processing for Virtual Reality
[ISCA 2019] Yue Leng*, Chi-chun Chen*, Qiuyue Sun, Jian Huang, Yuhao Zhu (* Co-primary authors)
Semantic-Aware Virtual Reality Video Streaming
[ApSys 2018] Yue Leng*, Chi-chun Chen*, Qiuyue Sun, Jian Huang, Yuhao Zhu (* Co-primary authors)

Augmented Reality

Hyperion: A 3D Visualization Platform for Optical Design of Folded Systems
[Frameless (Demo) 2019] Daniel K. Nikolov, Sifan Ye, Sydney Dlhopolsky, Zhen Bai, Yuhao Zhu, Jannick P. Rolland