相关论文: Learning to Generate Images with Perceptual Simila…

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual…

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A…

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and…

Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function.…

Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the freedom to optimize deep networks in different ways, make…

Existing reference (RF)-based super-resolution (SR) models try to improve perceptual quality in SR under the assumption of the availability of high-resolution RF images paired with low-resolution (LR) inputs at testing. As the RF images…

This paper proposes a new end-to-end trainable model for lossy image compression, which includes several novel components. The method incorporates 1) an adequate perceptual similarity metric; 2) saliency in the images; 3) a hierarchical…

Perceptual similarity scores that align with human vision are critical for both training and evaluating computer vision models. Deep perceptual losses, such as LPIPS, achieve good alignment but rely on complex, highly non-linear…

Traditional image similarity metrics are ineffective at evaluating the similarity between a real image of a scene and an artificially generated version of that viewpoint [6, 9, 13, 14]. Our research evaluates the effectiveness of a new,…

This paper proposes an explicit way to optimize the super-resolution network for generating visually pleasing images. The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

Generative adversarial networks (GAN) and generative diffusion models (DM) have been widely used in real-world image super-resolution (Real-ISR) to enhance the image perceptual quality. However, these generative models are prone to…

Deep neural networks have recently advanced the state-of-the-art in image compression and surpassed many traditional compression algorithms. The training of such networks involves carefully trading off entropy of the latent representation…

Recently, intermediate feature maps of pre-trained convolutional neural networks have shown significant perceptual quality improvements, when they are used in the loss function for training new networks. It is believed that these features…

Improving the performance on an imbalanced training set is one of the main challenges in nowadays Machine Learning. One way to augment and thus re-balance the image dataset is through existing deep generative models, like class-conditional…

We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that…

Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-oriented losses, such as L1 or L2. However, it has been shown…

Recently deep learning based image compression has made rapid advances with promising results based on objective quality metrics. However, a rigorous subjective quality evaluation on such compression schemes have rarely been reported. This…

Perceptual sound matching (PSM) aims to find the input parameters to a synthesizer so as to best imitate an audio target. Deep learning for PSM optimizes a neural network to analyze and reconstruct prerecorded samples. In this context, our…

In this paper, we propose a deep convolutional neural network for learning the embeddings of images in order to capture the notion of visual similarity. We present a deep siamese architecture that when trained on positive and negative pairs…