We describe a search-free resizing framework that can further improve the rate-distortion tradeoff of recent learned image compression models. Our approach is simple: compose a pair of differentiable downsampling/upsampling layers that sandwich a neural compression model. To determine resize factors for different inputs, we utilize another neural network jointly trained with the compression model, with the end goal of minimizing the rate-distortion objective. Our results suggest that "compression friendly" downsampled representations can be quickly determined during encoding by using an auxiliary network and differentiable image warping. By conducting extensive experimental tests on existing deep image compression models, we show results that our new resizing parameter estimation framework can provide Bj{\o}ntegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines. We also carried out a subjective quality study, the results of which show that our new approach yields favorable compressed images. To facilitate reproducible research in this direction, the implementation used in this paper is being made freely available online at: https://github.com/treammm/ResizeCompression.
翻译:我们描述一个可以进一步改进最近学习的图像压缩模型的速率扭曲取舍的无搜索重置框架。 我们的方法很简单: 组成一对不同的可下抽样/上抽样层, 并配以神经压缩模型。 为了确定不同投入的重新规模因素, 我们使用另一个与压缩模型共同培训的神经网络, 最终目标是将率扭曲目标降到最低。 我们的结果显示, “ 压缩友好” 下抽样演示在编码过程中可以通过使用辅助网络和不同图像扭曲来快速确定。 通过对现有深图像压缩模型进行广泛的实验测试, 我们展示的结果显示, 我们新的重定参数估计框架可以提供 Bj~ o}notegaard- Delta 率( BD- rate), 比前导感官质量引擎提高大约10% 。 我们还进行了主观质量研究, 研究结果显示, 我们的新方法可以产生有利的压缩图像。 为了便利此方向的再生研究, 本文中所使用的执行方式正在通过在线自由提供: https://githhubub.com/ remem/ resmas。