Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics

• URL: http://arxiv.org/abs/2402.02265v1
• Date: Sat, 3 Feb 2024 21:17:15 GMT
• Title: Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics
• Authors: Dror Freirich and Nir Weinberger and Ron Meir
• Abstract summary: We study the distortion-perception tradeoff over finite-alphabet channels. We show that computing the DP function and the optimal reconstructions is equivalent to solving a set of linear programming problems.
• Score: 31.383958289479015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whenever inspected by humans, reconstructed signals should not be distinguished from real ones. Typically, such a high perceptual quality comes at the price of high reconstruction error, and vice versa. We study this distortion-perception (DP) tradeoff over finite-alphabet channels, for the Wasserstein-$1$ distance induced by a general metric as the perception index, and an arbitrary distortion matrix. Under this setting, we show that computing the DP function and the optimal reconstructions is equivalent to solving a set of linear programming problems. We provide a structural characterization of the DP tradeoff, where the DP function is piecewise linear in the perception index. We further derive a closed-form expression for the case of binary sources.

Related papers

• Refined Risk Bounds for Unbounded Losses via Transductive Priors [58.967816314671296]
  We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression. Our key tools are based on the exponential weights algorithm with carefully chosen transductive priors.
  arXiv  Detail & Related papers  (2024-10-29T00:01:04Z)
• Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure [33.084834042565895]
  We study the rate-distortionperception (RDP) tradeoff for a memoryless source model in the limit of large blocklengths. Our perception measure is based on a divergence between the distributions of the source and reconstruction sequences conditioned on the encoder output.
  arXiv  Detail & Related papers  (2024-01-22T18:49:56Z)
• On the Computation of the Gaussian Rate-Distortion-Perception Function [10.564071872770146]
  We study the computation of the rate-distortion-perception function (RDPF) for a multivariate Gaussian source under mean squared error (MSE) distortion. We provide the associated algorithmic realization, as well as the convergence and the rate of convergence characterization. We corroborate our results with numerical simulations and draw connections to existing results.
  arXiv  Detail & Related papers  (2023-11-15T18:34:03Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction [60.95625458395291]
  In computed tomography (CT) the forward model consists of a linear transform followed by an exponential nonlinearity based on the attenuation of light according to the Beer-Lambert Law. We show that this approach reduces metal artifacts compared to a commercial reconstruction of a human skull with metal crowns.
  arXiv  Detail & Related papers  (2023-10-06T00:47:57Z)
• Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution [112.3443939502313]
  We propose a unified graph signal sampling framework which enjoys the benefits of graph signal analysis and processing. The key idea is to transform each user's ratings on the items to a function (signal) on the vertices of an item-item graph. For the online setting, we develop a Bayesian extension, i.e., BGS-IMC which considers continuous random Gaussian noise in the graph Fourier domain.
  arXiv  Detail & Related papers  (2023-02-08T08:17:43Z)
• Deep filter bank regression for super-resolution of anisotropic MR brain images [18.41979609846356]
  In 2D multi-slice magnetic resonance (MR) acquisition, the through-plane signals are typically of lower resolution than the in-plane signals. Super-resolution (SR) methods aim to recover the underlying high-resolution volume, but the estimated high-frequency information is implicit via end-to-end data-driven training. We propose a two-stage approach to approximate the completion of a perfect reconstruction filter bank corresponding to the anisotropic acquisition of a particular scan.
  arXiv  Detail & Related papers  (2022-09-06T16:05:19Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Physics-Enforced Modeling for Insertion Loss of Transmission Lines by Deep Neural Networks [4.762000720968522]
  We show that direct application of neural networks can lead to non-physics models with negative insertion loss. One solution is to add a regulation term, which represents the passive condition, to the final loss function to enforce the negative quantity of insertion loss. In the second method, a third-order expression is defined first, which ensures positiveness, to approximate the insertion loss.
  arXiv  Detail & Related papers  (2021-07-27T00:22:10Z)
• A Theory of the Distortion-Perception Tradeoff in Wasserstein Space [35.25746003630763]
  lower the distortion of an estimator, the more the distribution of its outputs deviates from the distribution of the signals it attempts to estimate. This phenomenon has captured significant attention in image restoration, where it implies that fidelity to ground truth images comes at the expense of perceptual quality. We show how estimators can be constructed from the estimators at the two extremes of the perception-distortion tradeoff.
  arXiv  Detail & Related papers  (2021-07-06T11:53:36Z)
• 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop [128.07841893637337]
  Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images. Minor deviation in parameters may lead to noticeable misalignment between the estimated meshes and image evidences. We propose a Pyramidal Mesh Alignment Feedback (PyMAF) loop to leverage a feature pyramid and rectify the predicted parameters.
  arXiv  Detail & Related papers  (2021-03-30T17:07:49Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.