Loss Functions for Neural Networks for Image Processing
Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much attention in the context of image processing: the default and virtually only choice is L2. In this paper, we bring attention to alternative choices for image restoration. In particular, we show the importance of perceptually-motivated losses when the resulting image is to be evaluated by a human observer. We compare the performance of several losses, and propose a novel, differentiable error function. We show that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged.
Code (2)
Tasks
Image RestorationSimilar Papers 제목 키워드 기반
LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents
We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image proces…
Image Super-ResolutionLarge Language ModelPrompt EngineeringSuper-ResolutionSimplifying Low-Light Image Enhancement Networks with Relative Loss Functions
Image enhancement is a common technique used to mitigate issues such as severe noise, low brightness, low contrast, and color deviation in low-light images. However, providing an optimal high-light image as a reference f…
Image EnhancementLow-Light Image EnhancementEvaluating Loss Functions and Learning Data Pre-Processing for Climate Downscaling Deep Learning Models
Deep learning models have gained popularity in climate science, following their success in computer vision and other domains. For instance, researchers are increasingly employing deep learning techniques for downscaling …
Deep LearningImage Super-ResolutionSuper-ResolutionUnveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective
Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processi…
Learning Euler's Elastica Model for Medical Image Segmentation
Image segmentation is a fundamental topic in image processing and has been studied for many decades. Deep learning-based supervised segmentation models have achieved state-of-the-art performance but most of them are limi…
Image SegmentationMedical Image SegmentationmodelSegmentation+1