Le An

Papers

Total Citations

H-Index

About

Le An is a researcher advancing the frontiers of computer vision, with a particular focus on efficient deep learning architectures for dense prediction tasks. His work is most notably recognized for pioneering the application of Transformer models to depth estimation, a critical challenge for autonomous systems and robotics. In his highly influential paper, "Depth Estimation with Simplified Transformer" (2022, 11 citations), An tackled the critical trade-off between state-of-the-art accuracy and real-time deployment. He demonstrated that a streamlined Transformer design could achieve competitive performance on monocular depth estimation while significantly reducing computational overhead, making it viable for latency-critical applications. This contribution directly addresses a major bottleneck in bringing advanced vision models to embedded and mobile platforms. By simplifying complex attention mechanisms without sacrificing representational power, An’s research provides a practical blueprint for efficient dense prediction, bridging the gap between cutting-edge research and real-world deployment. His work continues to inspire new directions in efficient vision transformers and their application to 3D scene understanding.