Sihaeng Lee

About

Sihaeng Lee is a computer vision researcher whose work focuses on monocular depth estimation and depth completion—critical technologies for robotics, autonomous driving, and 3D scene understanding. Lee’s most cited paper, “Patch-Wise Attention Network for Monocular Depth Estimation” (2021, 66 citations), introduces a novel attention mechanism that enables high-quality depth maps from single images, directly addressing a fundamental challenge in inferring 3D geometry from 2D data. Building on this, Lee proposed a “Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion” (2020, 42 citations), which fuses sparse laser scan data with RGB images to produce dense, accurate depth maps—overcoming the sparsity and noise that plague real-world sensor data. More recently, Lee developed “Multi-Scaled and Densely Connected Locally Convolutional Layers for Depth Completion” (2022), advancing the field with architectures that improve prediction fidelity for autonomous vehicle and robot vision applications. With over 110 citations across these works, Lee’s contributions are shaping how machines perceive depth in complex environments, bridging the gap between sparse sensor inputs and dense, actionable scene understanding.

Research Focus

Key Achievements

Top Papers

1. 1
   Patch-Wise Attention Network for Monocular Depth Estimation

   66 citations · 2021
2. 2
   Deep Architecture With Cross Guidance Between Single Image and Sparse LiDAR Data for Depth Completion

   42 citations · 2020
3. 3
   Multi-Scaled and Densely Connected Locally Convolutional Layers for Depth Completion

   3 citations · 2022

Key Collaborators

Contact & Links