Physics

Pattern recognition (psychology)

Feature (linguistics)

Image (mathematics)

Philosophy

Ground truth

Artificial intelligence

Network architecture

Power (physics)

Generative adversarial network

Discriminator

Computer science

Linguistics

Quantum mechanics

Generator (circuit theory)

Computer vision

Adversarial system

Computer security

Generative grammar

Artificial neural network

Telecommunications

Detector

IEEE Signal Processing Letters

De-raining, which aims at rain-steak removal from images, is a practical task in computer vision. However, it is difficult due to its ill-posed nature. In this letter, we propose a deep neural network architecture, feature-supervised generative adversarial network (FS-GAN) for single-image rain removal. Its main idea is to train a generative adversarial network (GAN) for which the supervision from ground truth is imposed on different layers of the generator network. We design a feature-supervised generator, a discriminator, an optimization target, as well as the detailed structure of FS-GAN. Experiments show that the proposed FS-GAN achieves better performance than state-of-the-art de-raining methods on both synthetic and real-world images in terms of quantitative and visual quality.

Single-Image De-Raining With Feature-Supervised Generative Adversarial Network