Kihwan Kim

Papers

Total Citations

246

H-Index

About

Kihwan Kim is a leading researcher in computer vision and 3D scene understanding, with a particular focus on reconstructing three-dimensional geometry from two-dimensional images. His most influential contribution is the development of PlaneRCNN, a groundbreaking deep neural architecture that detects and reconstructs piecewise planar surfaces from a single RGB image. By adapting Mask R-CNN to simultaneously predict plane parameters, segmentation masks, and refined depth maps, PlaneRCNN enables robust 3D plane detection and reconstruction—a critical capability for applications in augmented reality, robotics, and autonomous navigation. The 2019 paper on this work has garnered approximately 240 citations, underscoring its significant impact on the field. Kim’s research elegantly bridges the gap between 2D perception and 3D understanding, offering a practical solution for inferring the layout of indoor and outdoor scenes from minimal input. His work continues to inspire advances in single-image 3D reconstruction and remains a key reference for researchers exploring planar scene parsing and geometry-aware deep learning.