Share Email Print

Proceedings Paper • new

Generate optical flow with conditional generative adversarial network
Author(s): Lingqi Wu; Zongqing Lu; Ting Tang; Qingmin Liao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

As the cGANs achieves great success on pix to pix problem [12], we proposed a new architecture based on cGAN to solve our optical flow estimation problem. Specifically, we propose a loss function which consists of an adversarial loss and a content loss. The adversarial loss is the pixel-to-pixel loss. We use a discriminator network which is trained to differentiate the ground-truth flow and the generated flow on pixel space. The content loss focuses on perceptual similarity of the ground-truth flow and the generated flow. Our architecture (FlowGan) contains a generator based on FlowNetS with Dense Block to make it deeper and a Markovian discriminator to classify image patch instead of the whole image. We train our network with FlyingChairs datasets and evaluated our network on MPISintel. FlowGan can get competitive results with practical speed.

Paper Details

Date Published: 9 August 2018
PDF: 8 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108064J (9 August 2018); doi: 10.1117/12.2503297
Show Author Affiliations
Lingqi Wu, Tsinghua Univ. (China)
Zongqing Lu, Tsinghua Univ. (China)
Ting Tang, Tsinghua Univ. (China)
Qingmin Liao, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top