arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.03123eess.IVcs.CVcs.LG
收藏

COIN:内隐神经表征的压缩

COIN: COmpression with Implicit Neural representations

University of Oxford(牛津大学)

Emilien Dupont, Adam Goliński, Milad Alizadeh, Yee Whye Teh, Arnaud Doucet

摘要:

我们提出了一种新的简单的方法来进行图像压缩:我们存储过拟合到图像的神经网络的权重,而不是存储图像的每个像素的RGB值。具体来说,为了对图像进行编码,我们将其与将像素位置映射到RGB值的MLP相匹配。然后,我们将该MLP的权重存储为图像的代码。为了解码图像,我们简单地评估每个像素位置的MLP。我们发现,这种简单的方法在低比特率下优于JPEG,即使没有熵编码或学习权重分布。虽然我们的框架还没有竞争力的最先进的压缩方法,我们表明,它具有各种有吸引力的属性,这可能使它成为一个可行的替代其他神经数据压缩方法。

英文摘要:

We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP which maps pixel locations to RGB values. We then quantize and store the weights of this MLP as a code for the image. To decode the image, we simply evaluate the MLP at every pixel location. We found that this simple approach outperforms JPEG at low bit-rates, even without entropy coding or learning a distribution over weights. While our framework is not yet competitive with state of the art compression methods, we show that it has various attractive properties which could make it a viable alternative to other neural data compression approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑