Can I read Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light on EtoBox?

Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light by Jung, Eunah; Yang, Nan; Cremers, Daniel is a scholarly article available to read on EtoBox.

What is Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light about?

We propose the concept of a multi-frame GAN (MFGAN) and demonstrate its potential as an image sequence enhancement for stereo visual odometry in low light conditions. We base our method on an invertible adversarial network to transfer the beneficial features of brightly illuminated scenes to the sequence in poor illumination without costly paired datasets. In order to preserve the coherent geometric cues for the translated sequence, we present a novel network architecture as well as a novel loss term combining temporal and stereo consistencies based on optical flow estimation. We demonstrate that the enhanced sequences improve the performance of state-of-the-art feature-based and direct stereo visual odometry methods on both synthetic and real datasets in challenging illumination. We also show that MFGAN outperforms other state-of-the-art image enhancement and style transfer methods by a large margin in terms of visual odometry.

Author

Jung, Eunah; Yang, Nan; Cremers, Daniel

Published

2019

Language

EN