Max Robotics — Global Service Robot Directory + US Certification

About

Liren Jin is a robotics and computer vision researcher whose work sits at the intersection of autonomous perception, neural scene representations, and active view planning. His research addresses a fundamental challenge in robotics: how to intelligently position cameras to gather the most informative data about unknown environments under real-world resource constraints. Jin's most recognized contribution, "NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Rendering" (2023), has garnered 39 citations and introduced a novel framework that leverages uncertainty estimation within neural radiance fields to guide autonomous camera placement—a significant step forward in active reconstruction. His subsequent work has continued to push this frontier, including "ActiveGS" (2025), which proposes a hybrid Gaussian splatting approach for real-time scene mapping with RGB-D cameras, and research exploiting 3D diffusion model priors to enable efficient one-shot view planning for object reconstruction. Collectively, Jin's publications reflect a coherent research vision: making autonomous robots smarter and more efficient perceivers. By combining cutting-edge neural rendering techniques with principled uncertainty-driven planning, his work is shaping how robots can actively and adaptively explore their environments—a capability critical for manipulation, inspection, and beyond.