To mitigate this, we propose the simple and effective Semantic-aware Discriminator (denoted as SeD), which encourages the SR network to learn the fine-grained distributions by introducing the semantics of images as a condition. Concretely, we aim to excavate the semantics of imag...
This repository is the official PyTorch implementation of SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR24) 🔖 News!!! 2024-3-24: Updated training codes! 2024-4-11: Updated test codes and U+SeD. Generative Adversarial Networks (GANs) have been widely used to recover vivid...
Moreover, the patch discriminator is introduced to judge the patches of inpainting image are real or fake. In this way, our network can effectively utilize the semantic information to complete a fine result. Furthermore, both perceptual loss and style loss are used to improve the inpainting ...
Then, we compare the discriminating result of image patches among P ′, the worst patch is most likely to be 'fake' and can be chosen to update parameters of both discriminator and generator. Hence, the discriminator plausibly uses the semantic priors to find ...
In this paper we propose a new conditional GAN for image captioning that enforces semantic alignment between images and captions through a co-attentive discriminator and a context-aware LSTM sequence generator. In order to train these se... I Melnyk,T Sercu,PL Dognin,... 被引量: 3发表: ...
an adversarial game between a generator and a discriminator, and then utilizes the generator to produce a fused image with primary infrared intensity and additional visible gradients, and finally forces the fused image to have more details present in the visible image through the discriminator. And...
It embeds the frequency-aware categorizer (FAC) into the discriminator to determine the input veracity in the spatial and spectral domains. Besides, semantic restricted sampling is employed in SFGAN for synthesizing the image subject to a semantic mask. Further, the created sam...
SAGAN [31] applies the self-attention model in the field of image generation, capturing more information from all feature map positions, and the discriminator can establish the correlation between different pixels even if under long-distance conditions, which is an improvement of the effect in ...