paper-with-me

Papers

Lossy Image Compression with Quantized Hierarchical VAEs

2022-08-27 · Zhihao Duan, Ming Lu, Zhan Ma, Fengqing Zhu

Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative modeling. Starting with ResNet VAEs, which are originally designed for data (image) distribution modeling, we redesign their latent variable model using a quantization-aware posterior and prior, enabling easy quantization and entropy coding at test time. Along with improved neural network architecture, we present a powerful and efficient model that outperforms previous methods on natural image lossy compression. Our model compresses images in a coarse-to-fine fashion and supports parallel encoding and decoding, leading to fast execution on GPUs. Code is available at https://github.com/duanzhiihao/lossy-vae.

📄 PDF Abstract BibTeX arXiv:2208.13056

Code (2)

duanzhiihao/lossy-vae 공식 구현 pytorch
duanzhiihao/qres-vae pytorch

Tasks

Image CompressionQuantization

Methods 이 논문이 사용한 방법론

Test 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Hierarchical Quantized Autoencoders

2020-02-19 · NeurIPS 2020 12 · Will Williams, Sam Ringer, Tom Ash, John Hughes 외

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning d…

Image CompressionQuantization

QARV: Quantization-Aware ResNet VAE for Lossy Image Compression

2023-02-16 · Zhihao Duan, Ming Lu, Jack Ma, Yuning Huang 외

This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of varia…

Image CompressionQuantization

Improving Inference for Neural Image Compression

2020-06-07 · NeurIPS 2020 12 · Yibo Yang, Robert Bamler, Stephan Mandt

We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn inference networks to predict a compressible l…

Image CompressionVariational Inference

Learning Scalable lY=-Constrained Near-Lossless Image Compression via Joint Lossy Image and Residual Compression

2021-06-19 · CVPR 2021 1 · Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang 외

We propose a novel joint lossy image and residual compression framework for learning l_infinity-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through los…

Image Compression

Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression

2021-03-31 · Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang 외

We propose a novel joint lossy image and residual compression framework for learning $\ell_\infty$-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through loss…

Image Compression