Ruijie Ren

Papers

Total Citations

H-Index

About

Ruijie Ren is an emerging researcher at the intersection of robotics, computer vision, and deep learning, with a focused expertise in spatial understanding and scene representation for autonomous systems. Their work addresses some of the most pressing challenges in enabling robots to perceive and navigate complex, real-world environments reliably and intelligently. Ren's most recognized contribution, "MaskVO: Self-Supervised Visual Odometry with a Learnable Dynamic Mask" (2022, 9 citations), tackles a fundamental limitation in visual odometry — the interference of dynamic objects when estimating robot ego-motion. By introducing a learnable dynamic mask within a self-supervised framework, the work advances the robustness of pose and depth estimation without requiring manually labeled data, a significant practical achievement. Complementing this, Ren's research on uncertainty quantification for Neural Radiance Fields (NeRF) addresses a critical gap in 3D scene reconstruction. By developing methods to estimate uncertainty in unseen or occluded regions, Ren enhances the reliability of NeRF-based systems for robotics applications where safety-critical decision-making demands trustworthy predictions (6 citations). Together, these contributions position Ren as a promising voice in robot perception research, bridging self-supervised learning and principled uncertainty estimation for real-world deployment.