no code implementations • 24 Sep 2024 • Jinchang Zhang, Guoyu Lu
3D object reconstruction based on deep neural networks has gained increasing attention in recent years.
no code implementations • 18 Sep 2024 • Jinchang Zhang, Ningning Xu, Hao Zhang, Guoyu Lu
By learning the blur levels at different focal distances of the same scene in the focal stack, the framework predicts the defocus map and Circle of Confusion (CoC) from a single defocused image, using the defocus map as input to DepthNet for monocular depth estimation.
no code implementations • 2 Aug 2024 • Jinchang Zhang, Praveen Kumar Reddy, Xue-Iuan Wong, Yiannis Aloimonos, Guoyu Lu
Depth estimation is a critical topic for robotics and vision-related tasks.