ZHANG Bo

Hello! I am Bo, now a research engineer at Li Auto, where I work on camera and vision. I specialize in camera-AI co-design, RAW-domain enhancement and perception, and physics-based image data synthesis. I did my PhD at Tsinghua University, where I was advised by Jinli Suo. I obtained my bachelor's degree from the Department of Precision Instruments, Tsinghua University.

Email / Scholar / Github / LinkedIn

Research

I'm interested in computer vision, computational imaging, image processing and deep learning. I am familiar with optics, camera and image processing algorithms. My research is about developing optical systems and algorithms to enhance imaging quality for human vision and applications. Previous projects involve low-light enhancement/object detection, snapshot compressive imaging and event camera vision.

	DarkVision: A benchmark and study for low-light image/video analysis Bo Zhang, Yuchen Guo, Runzhao Yang, Zhihong Zhang, Jiayi Xie, Jinli Suo, Qionghai Dai CVM, 2026 Dataset link Building a large-scale benchmark for low-light image and video perception, including enhancement and object detection.
	Event-Enhanced Snapshot Compressive Videography at 10K FPS Bo Zhang, Jinli Suo, Qionghai Dai TPAMI, 2024 Integrating an event camera into snapshot compressive imaging and realizing 10K FPS imaging with a snapshot measurement and sparse events.
	Real-Time Sketching of Harshly Lit Driving Environment Perception by Neuromorphic Sensing Yuqi Han, Jinli Suo, Bo Zhang, Jiachen Zhao, Yuxiao Cheng, Qionghai Dai TIV, 2024 Utilizing ana event camera for real-time sketching of driving environments under extreme lighting conditions.
	An event-oriented diffusion-refinement method for sparse events completion Bo Zhang, Yuqi Han, Jinli Suo, Qionghai Dai Scientific Reports, 2024 Developing a diffusion model that completes sparse events with high fidelity to enable human observation and dowstream applications.
	A complementary dual-backbone transformer extracting and fusing weak cues for object detection in extremely dark videos Bo Zhang, Jinli Suo, Qionghai Dai Information Fusion, 2024 Developing a dual-backbone Transformer for accurate video object detection in low-light scenarios.
	From compressive sampling to compressive tasking: retrieving semantics in compressed domain with low bandwidth Zhihong Zhang, Bo Zhang*, Xin Yuan, Siming Zheng, Xiongfei Su, Jinli Suo, David J. Brady, Qionghai Dai PhotoniX*, 2022 A survey for semantic tasks in comressed domain.
	Snapshot compressive imaging based digital image correlation: temporally super-resolved full-resolution deformation measurement Wenwu Chen, Bo Zhang, Liuning Gu, Haibo Liu, Jinli Suo, Xinxing Shao Optics Express, 2022 SCI meets DIC.
	NeRFE: Free View Synthesis for Event Data Bo Zhang, Yuqi Han, Jinli Suo, Qionghai Dai International Conference on Guidance, Navigation and Control, 2022 Developing a neural radiance field method for event cameras to enable high-quality view synthesis.
	End-to-end snapshot compressed super-resolution imaging with deep optics Bo Zhang, Xin Yuan, Chao Deng, Zhihong Zhang, Jinli Suo, Qionghai Dai Optica, 2022 Integrating deep optics into snapshot compressive imaging to achieve high-quality super-resolution imaging from a single snapshot measurement.

Academic Services

Reviewer for CVPR, ECCV, Photonics Research, Optics Express, Applied Optics, Optics Continuum.

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.