Nobuhiko Wakai — accepted AI-conference papers

2024

Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption

Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii, Takayoshi Yamashita

CVPR 2024poster

A Manhattan world lying along cuboid buildings is useful for camera angle estimation. However accurate and robust angle estimation from fisheye images in the Manhattan world has remained an open challenge because general scene images tend to lack constraints such as lines arcs and vanishing points.…

Cited by 3 Source ↗PDF ↗Scholar ↗

2022

Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion

Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii, Takayoshi Yamashita

ECCV 2022poster

"Although recent learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, the accuracy of these methods is degraded in fisheye images. This degradation is caused by mismatching between the actual projection and expected projection. To address this…

Cited by 9 Source ↗PDF ↗Scholar ↗