CM-GAN-Inpainting
Image Inpainting Framework
A deep learning framework for image inpainting using a cascaded modulation GAN design with object-aware training and spatial adaptive modulation.
CM-GAN for Image Inpainting
243 stars
21 watching
20 forks
Language: Python
last commit: 4 months ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
| Unsupervised feature learning by image inpainting using Generative Adversarial Networks (GANs) | 887 |
| Software framework for training and evaluating generative models of images and text based on adversarial networks | 847 |
| A software framework for generating art-inspired images using deep learning techniques | 412 |
| An algorithm for blending two images together to create realistic high-resolution images | 463 |
| A collection of MATLAB implementations for Generative Adversarial Networks (GANs) and related deep learning techniques | 190 |
| This project explores image colorization using generative adversarial networks on the CIFAR10 dataset. | 11 |
| A PyTorch implementation of a generative adversarial network for image synthesis from text descriptions | 1,863 |
| A PyTorch implementation of a deep learning model for inpainting images using contextual information | 366 |
| An implementation of a deep learning-based makeup transfer algorithm that can robustly handle pose and expression variations in images. | 737 |
| A TensorFlow implementation of generating images from text descriptions using a Generative Adversarial Network (GAN) architecture | 602 |
| A deep learning framework providing a model architecture and training code for image captioning using semantic compositional networks | 70 |
| A Python implementation of a Generative Adversarial Network (GAN) model used to generate portraits from latent codes. | 40 |
| A PyTorch-based framework for 3D scene understanding with holistic context graph and relation-based optimization in panoramic images | 90 |
| Deep learning implementation of image matting, aiming to separate foreground and background from input images. | 293 |
| This implementation enables text-to-image generation by leveraging cross-modal contrastive learning. | 98 |