Zhenwen Ren

Southwest University of Science and Technology

Papers

Total Citations

H-Index

About

Zhenwen Ren is a researcher at the forefront of computer vision and robotics, with key contributions spanning image retrieval, 3D scene understanding, and multi-robot coordination. Ren’s most cited work, “Relaxed Energy Preserving Hashing for Image Retrieval” (2024, 19 citations), addresses a critical bottleneck in industrial robotics: efficient visual search. By advancing learning-to-hash techniques, this work enhances machine visual search, street view recognition, and object grasping—directly impacting autonomous systems. In “Scale-flow” (2022, 6 citations), Ren tackles normalized scene flow estimation from RGB video, enabling precise 3D motion analysis for action prediction and autonomous robot navigation. This dual focus on optical flow and motion-in-depth provides a powerful tool for dynamic environments. Earlier, Ren contributed to robotics infrastructure with “Quick Two-Way Time Message Exchange for Time Synchronization in Robot Networks” (2018, 2 citations), improving coordination in quadrotor groups by addressing variable response latency in time synchronization protocols. Across these works, Ren demonstrates a consistent drive to solve practical challenges—from visual perception to network synchronization—making their research highly relevant for students and engineers building next-generation autonomous systems.