Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
arXiv:1703.10114
Abstract
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that lead to this state-of-the-art result. First, we show that training with a pixel-wise loss weighted by SSIM increases reconstruction quality according to several metrics. Second, we modify the recurrent architecture to improve spatial diffusion, which allows the network to more effectively capture and propagate image information through the network's hidden state. Finally, in addition to lossless entropy coding, we use a spatially adaptive bit allocation algorithm to more efficiently use the limited number of bits to encode visually complex image regions. We evaluate our method on the Kodak and Tecnick image sets and compare against standard codecs as well recently published methods based on deep neural networks.
References in corpus (6)
Cited by in corpus (21)
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Video Compression With Rate-Distortion Autoencoders
- Learning for Video Compression
- Real-Time Adaptive Image Compression
- Towards Image Understanding from Deep Compression without Decoding
- Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
- Fixing a Broken ELBO
- Generalized Octave Convolutions for Learned Multi-Frequency Image Compression
- Video Compression through Image Interpolation
- Human Perceptual Evaluations for Image Compression
- Deep Generative Models for Distribution-Preserving Lossy Compression
- Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression
- DSSLIC: Deep Semantic Segmentation-based Layered Image Compression
- Learning a Single Tucker Decomposition Network for Lossy Image Compression with Multiple Bits-Per-Pixel Rates
- Perceptual Quality Study on Deep Learning based Image Compression
- Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods
- Neural Multi-scale Image Compression
- Learning Compressible 360° Video Isomers
- Learning Image and Video Compression through Spatial-Temporal Energy Compaction
- Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks
- Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods