Sep 5, 2024 · We propose a novel method that incorporates Multi-Objective Optimization (MOO) into the training process of SISR models to balance perceptual quality and ...
The work proposes a Single-image super-resolution (SISR) algorithm that uses a multi-objective optimization (MOO) method. The method balances perceptual quality ...
Oct 28, 2024 · In this paper, we introduce a novel approach to single-image super-resolution (SISR) that balances perceptual quality and distortion through multi-objective ...
Dec 24, 2023 · In this paper, we formulate the perception-distortion trade-off in SR as a multi-objective optimization problem and develop a new optimizer.
In this paper, we formulate the perception-distortion trade-off in SR as a multi-objective optimization problem and develop a new optimizer by integrating the ...
Implementation of MOBOSR with settings identical to ESRGAN, but employing multi-objective Bayesian optimization to dynamically adjust loss weights during the ...
In this paper, we proposed a hybrid EA-Adam optimization method to optimize the perception-distortion balanced image super-resolution (SR) models. We formulated ...
People also ask
What is an example of a multi-objective optimization problem?
What is the difference between multi-objective optimization and many objective optimization?
This paper forms the perception-distortion trade-off in SR as a multi-objective optimization problem and develops a new optimizer by integrating the ...
High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR).
Aug 1, 2024 · In this paper, we formulate the perception-distortion trade-off in SR as a multi-objective optimization problem and develop a new optimizer by ...