Summary
Qingan Yan is a Staff Research Scientist and Tech Lead based in Palo Alto with nine years of experience building 3D computer vision and embodied AI systems for consumer devices and research. He leads R&D at OPPO’s US research center on neural 3D reconstruction, scene understanding, semantic segmentation, depth estimation and vision-language navigation, translating foundational research into XR and wearable applications. Previously he drove 3D modeling and virtual try-on projects at JD.com and developed multi-view stereo and texture synthesis methods during his Ph.D. at Wuhan University. Comfortable spanning theory and engineering, he combines deep academic training with product-focused delivery, routinely bridging SLAM, multimodal foundation models and real-time constraints. Outside of work he signs code and notes with a musical nod—“Canon in D”—hinting at a detail-oriented, creative approach to complex visual problems.
9 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Vision and Graphics, Doctor of Philosophy (Ph.D.), Computer Vision and Graphics at Wuhan University
Master of Science (M.S.), Computer Vision, Virtual Reality and Human-Computer Interaction, Master of Science (M.S.), Computer Vision, Virtual Reality and Human-Computer Interaction at Southwest University of Science and Technology
Bachelor of Engineering (B.E.), Computer Science, Bachelor of Engineering (B.E.), Computer Science at Hubei Minzu University
Chinese, English