no code implementations • 9 Sep 2020 • Jesper Haahr Christensen, Lars Valdemar Mogensen, Ole Ravn
Our focus in this work is solely on learning to reconstruct the high-resolution images on "real-world" data.
no code implementations • 16 Jun 2020 • Jesper Haahr Christensen, Lars Valdemar Mogensen, Ole Ravn
In this work, we investigate a Deep Learning (DL) approach to fish segmentation in a small dataset of noisy low-resolution images generated by a forward-looking multibeam echosounder (MBES).
1 code implementation • 14 Jun 2020 • Jesper Haahr Christensen, Sascha Hornauer, Stella Yu
We improve on the previous model by introducing several changes to the model, which leads to a better depth and grayscale estimation, and increased perceptual quality.
1 code implementation • 15 Dec 2019 • Jesper Haahr Christensen, Sascha Hornauer, Stella Yu
Inspired by bats' echolocation mechanism, we design a low-cost BatVision system that is capable of seeing the 3D spatial layout of space ahead by just listening with two ears.