Huai-Jen Liang

Papers

Total Citations

H-Index

About

Huai-Jen Liang is a leading researcher in computer vision and robotics, specializing in visual odometry (VO) and simultaneous localization and mapping (SLAM). His work bridges the gap between traditional geometric approaches and modern semantic understanding, with a focus on enabling robust perception in cluttered indoor environments. Liang’s most notable contribution is "SalientDSO: Bringing Attention to Direct Sparse Odometry" (2019), which has garnered 73 citations. This paper pioneers the integration of high-level semantic information—such as object saliency—into direct sparse odometry, moving beyond reliance on geometric features like points and lines. By jointly optimizing geometric and semantic cues, SalientDSO significantly improves localization accuracy in complex scenes where conventional VO algorithms fail. This work has influenced subsequent research in attention-driven SLAM systems. Liang’s research is highly impactful, with his papers cited extensively in the fields of autonomous navigation, augmented reality, and mobile robotics. His innovative approach to fusing semantics with geometry has opened new pathways for more intelligent and adaptive perception systems, making him a key figure in advancing real-world robotic vision.