Deep Perceptual Compression

Abstract

Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function. Unfortunately, neither of these correlate well with human perception and this is clearly visible from the resulting compressed images. In several cases, the MS-SSIM for deep learned techniques is higher than say a conventional, non-deep learned codec such as JPEG-2000 or BPG. However, the images produced by these deep learned techniques are in many cases clearly worse to human eyes than those produced by JPEG-2000 or BPG. We propose the use of an alternative, deep perceptual metric, which has been shown to align better with human perceptual similarity. We then propose Deep Perceptual Compression (DPC) which makes use of an encoder-decoder based image compression model to jointly optimize on the deep perceptual metric and MS-SSIM. Via extensive human evaluations, we show that the proposed method generates visually better results than previous learning based compression methods and JPEG-2000, and is comparable to BPG. Furthermore, we demonstrate that for tasks like object-detection, images compressed with DPC give better accuracy.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Pixel Recurrent Neural Networks
• Variational image compression with a scale hyperprior
• End-to-end Optimized Image Compression
• Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
• Joint Autoregressive and Hierarchical Priors for Learned Image Compression
• Density Modeling of Images using a Generalized Normalization Transformation
• Context-adaptive Entropy Model for End-to-end Optimized Image Compression
• Lossy Image Compression with Compressive Autoencoders
• Real-Time Adaptive Image Compression

Cited by in corpus (6)

• Hierarchical Quantized Autoencoders
• Human Perceptual Evaluations for Image Compression
• Learning to Compress Videos without Computing Motion
• CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network
• CompressNet: Generative Compression at Extremely Low Bitrates
• Saliency Driven Perceptual Image Compression