Feature Forwarding for Efficient Single Image Dehazing
| Autor: | Tzofi Klinghoffer, Peter Morales, Seung Jae Lee |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Artificial neural network 65D19 I.4.4 business.industry Computer science Image quality Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Convolutional neural network Image (mathematics) Feature (computer vision) Pyramid 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Pyramid (image processing) Enhanced Data Rates for GSM Evolution Artificial intelligence business Cropping Image resolution |
| Zdroj: | CVPR Workshops |
| DOI: | 10.1109/cvprw.2019.00260 |
| Popis: | Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to run on edge graphical processing units (GPUs). We utilize three variants of our architecture to explore the dependency of dehazed image quality on parameter count and model design. The first two variants presented, a small and big version, make use of a single efficient encoder-decoder convolutional feature extractor. The final variant utilizes a pair of encoder-decoders for atmospheric light and transmission map estimation. Each variant ends with an image refinement pyramid pooling network to form the final dehazed image. For the big variant of the single-encoder network, we demonstrate state-of-the-art performance on the NYU Depth dataset. For the small variant, we maintain competitive performance on the super-resolution O/I-HAZE datasets without the need for image cropping. Finally, we examine some challenges presented by the Dense-Haze dataset when leveraging CNN architectures for dehazing of dense haze imagery and examine the impact of loss function selection on image quality. Benchmarks are included to show the feasibility of introducing this approach into real-time systems. Accepted to the NTIRE 2019 CVPR Workshop. Paper number 77. 8 Pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|