PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation

no code implementations • 3 Jun 2020 • Noriaki Hirose, Satoshi Koide, Keisuke Kawano, Ruho Kondo

We propose a novel objective for penalizing geometric inconsistencies to improve the depth and pose estimation performance of monocular camera images.

Monocular Depth Estimation Pose Estimation

Flow-based Image-to-Image Translation with Feature Disentanglement

no code implementations • NeurIPS 2019 • Ruho Kondo, Keisuke Kawano, Satoshi Koide, Takuro Kutsuna

Learning non-deterministic dynamics and intrinsic factors from images obtained through physical experiments is at the intersection of machine learning and material science.

Disentanglement Image-to-Image Translation +1