Satoshi Sakuma

Papers

Total Citations

H-Index

About

Satoshi Sakuma is a computer vision researcher whose work centers on 3D object recognition and pose estimation from single 2D images. His most cited contribution, "Pose Determination of 3-D Object from a Single Perspective View" (1996), addresses a fundamental challenge in computer vision: accurately determining the spatial orientation and position of a 3D polyhedral object using only one perspective image. The method relies on known 3D prototype models and requires establishing vertex correspondences and coordinate transformation parameters. While this specific paper has accumulated 3 citations, it represents foundational work in the field of monocular 3D reconstruction. Sakuma's research sits at the intersection of geometry, computer vision, and robotics, contributing to applications in automated manufacturing, object tracking, and augmented reality. His approach to solving the correspondence problem between 2D image features and 3D model vertices has influenced subsequent work in model-based vision. For students and researchers exploring pose estimation, Sakuma's work offers a clear, mathematically grounded entry point into understanding how single-view geometry can recover 3D structure—a problem that remains central to modern computer vision systems.