Darvin Yi

Papers

Total Citations

H-Index

About

Darvin Yi is a researcher at the intersection of computer vision, deep learning, and indoor spatial understanding. His most-cited work, "DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences" (2019, 9 citations), introduces a novel deep learning pipeline that infers complete indoor perimeter maps—essentially exterior boundary layouts—from sequences of posed RGB images. By leveraging robust deep methods for depth estimation and wall segmentation, Yi’s approach generates a coherent exterior boundary point cloud, enabling accurate room shape reconstruction without relying on expensive LiDAR or multi-view setups. This contribution is particularly impactful for applications in robotics, augmented reality, and architectural modeling, where understanding indoor geometry from simple camera input is critical. Though his citation count is modest, Yi’s work demonstrates a clear focus on practical, data-driven solutions for spatial inference. His research stands out for its integration of classical geometric reasoning with modern deep learning, offering a scalable path to indoor mapping that could influence future work in scene understanding and autonomous navigation.