Wenjie Wang

Papers

Total Citations

H-Index

About

Wenjie Wang is an emerging researcher specializing in computer vision and 3D scene understanding, with a particular focus on object pose estimation — a critical challenge in robotics, augmented reality, and autonomous systems. His notable work, "A Novel Adaptive Weighted Fusion Network Based on Pixel Level Feature Importance for Two-Stage 6D Pose Estimation" (2025), introduces an innovative approach to determining the precise position and orientation of objects in three-dimensional space. By leveraging pixel-level feature importance within an adaptive weighted fusion framework, Wang's method advances the accuracy and robustness of 6D pose estimation pipelines, addressing longstanding limitations in multi-modal feature integration. Though early in its citation trajectory with 3 citations since publication, the recency of this work signals a researcher actively pushing boundaries at the frontier of his field. Wang's contributions reflect a deep engagement with deep learning architectures and their practical applications in perception systems. As demand for reliable 6D pose estimation grows across industrial automation and intelligent robotics, Wang's research positions him as a promising voice shaping the next generation of computer vision solutions.