Related papers: On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

URL: http://arxiv.org/abs/2106.02782v1
Date: Sat, 5 Jun 2021 02:53:38 GMT
Title: On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
Authors: Zeyu Yan, Fei Wen, Rendong Ying, Chao Ma, and Peilin Liu
Abstract summary: We show that the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion. We propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate.
Score: 12.13586501618741
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion (e.g., MSE). This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder. Further, we propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate. This framework uses a GAN with discriminator conditioned on an MSE-optimized encoder, which is superior over the traditional framework using distortion plus adversarial loss. Experiments are provided to verify the theoretical finding and demonstrate the superiority of the proposed training framework.

Related papers

Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption [57.056311855630916]
We propose a Controllable Generative Image Compression framework, Control-GIC. It is capable of fine-grained adaption across a broad spectrum while ensuring high-fidelity and generality compression. We develop a conditional conditionalization that can trace back to historic encoded multi-granularity representations.
arXiv Detail & Related papers (2024-06-02T14:22:09Z)
Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
arXiv Detail & Related papers (2024-01-25T08:11:27Z)
Optimally Controllable Perceptual Lossy Compression [16.208548355509127]
Recent studies in lossy compression show that distortion and perceptual quality are at odds with each other. To attain different perceptual quality, different decoders have to be trained. We present a nontrivial finding that only two decoders are sufficient for optimally achieving arbitrary D-P tradeoffs.
arXiv Detail & Related papers (2022-06-21T02:48:35Z)
Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
arXiv Detail & Related papers (2022-02-09T18:48:02Z)
Optimal Rate Adaption in Federated Learning with Compressed Communications [28.16239232265479]
Federated Learning incurs high communication overhead, which can be greatly alleviated by compression for model updates. tradeoff between compression and model accuracy in the networked environment remains unclear. We present a framework to maximize the final model accuracy by strategically adjusting the compression each iteration.
arXiv Detail & Related papers (2021-12-13T14:26:15Z)
Universal Rate-Distortion-Perception Representations for Lossy Compression [31.28856752892628]
We consider the notion of universal representations in which one may fix an encoder and vary the decoder to achieve any point within a collection of distortion and perception constraints. We prove that the corresponding information-theoretic universal rate-distortion-perception is operationally achievable in an approximate sense.
arXiv Detail & Related papers (2021-06-18T18:52:08Z)
Substitutional Neural Image Compression [48.20906717052056]
Substitutional Neural Image Compression (SNIC) is a general approach for enhancing any neural image compression model. It boosts compression performance toward a flexible distortion metric and enables bit-rate control using a single model instance.
arXiv Detail & Related papers (2021-05-16T20:53:31Z)
Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression [118.89112502350177]
We propose a novel framework for learning $ell_infty$-constrained near-lossless image compression. We derive the probability model of the quantized residual by quantizing the learned probability model of the original residual.
arXiv Detail & Related papers (2021-03-31T11:53:36Z)
Perceptually Optimizing Deep Image Compression [53.705543593594285]
Mean squared error (MSE) and $ell_p$ norms have largely dominated the measurement of loss in neural networks. We propose a different proxy approach to optimize image analysis networks against quantitative perceptual models.
arXiv Detail & Related papers (2020-07-03T14:33:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.