Shukuan Lin

Papers

Total Citations

H-Index

About

Shukuan Lin is a computer vision researcher whose work focuses on advancing depth and pose estimation—fundamental challenges in robotics, autonomous driving, and virtual reality. Lin’s most notable contribution addresses the critical difficulty of supervised learning in environments where labeled data is scarce or unavailable. In their highly cited 2020 paper, Lin introduced a partial tracking method based on a siamese network, offering a novel approach to object tracking that has garnered 5 citations. Building on this, Lin’s 2021 work proposed a monocular weakly supervised depth and pose estimation method that leverages multi-information fusion, achieving accurate results without relying on costly ground-truth labels. This innovation is particularly impactful for real-world applications where labeled datasets are impractical. With a growing citation record and a focus on solving core computer vision problems, Lin’s research is paving the way for more robust, scalable autonomous systems. Their work stands out for its practical approach to bridging the gap between supervised and unsupervised learning in critical perception tasks.