按年被提到
20162016 · 1 次2026
视觉、语音与图像生成›超分辨率与图像压缩·arXiv:1609.05158 · cs.CV

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

Wenzhe Shi, Jose Caballero, Ferenc Huszár, Johannes Totz, Andrew P. Aitken, Rob Bishop, Daniel Rueckert, Zehan Wang · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-10-01 · 最近 2018-07-20
2不同的人
2活跃月份
2讨论串
7,533被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论trustswz · 2016-10

“If you are interested in how it compares to bicubic or the original. Check these papers using the sub pixel convolutional layer: https://arxiv.org/abs/1609.05158 https://arxiv.org/abs/1609.04802.”

Subpixel: A subpixel convolutional neural network implementation with Tensorflow原评论 ↗
评论akarve · 2018-07

“Quilt isn't doing the inference (the PyTorch model is). But, in any case, no. Super-resolution is more than blurring, it's pixel inference. https://arxiv.org/abs/1609.05158”

Reproducible machine learning with PyTorch and Quilt原评论 ↗