| Popis: |
End-to-end learned image and video codecs, based on auto-encoder architecture, adapt naturally to image resolution, thanks to their convolutional aspect. However, while coding high resolution images, these codecs face hardware problems such as memory saturation. This paper proposes a patch-based image coding solution based on an end-to-end learned model, which aims to remedy to the hardware limitation while maintaining the same quality as full resolution image coding. Our methodconsists in coding overlapping patches of the image and reconstruct them into a decoded image using a weighting function. This approach manages to be on par with the performance of full resolution image coding using an end-to-end learned model, and even slightly outperform it, while being adaptable to different memory size. It is also compatible with any learned codec based on a conv/deconvolutional autoencoderarchitecture without having to retrain the model. |
