Furukawa, Yasutaka

3D digital human reconstructions and avatars

Articulated object reconstruction from interaction videos

Cuboid-maps for indoor illumination modeling and augmented reality rendering

Data-driven methods for non-visual indoor localization and extreme pose estimation

Generalized dynamic human digitalization with sparse-view cameras

High resolution instance segmentation for building blueprint vectorization

Robust neural inertial navigation in the wild

Structural regularity learning for automated architecture modeling

Structured outdoor architecture reconstruction through RGB image

Towards automating 3D computer-aided design with deep generative model