Massachusetts Institute of Technology researchers had created convinient image editor, based on AI
23 August 2018
Researchers from the Massachusetts Institute of Technology (MIT) presented an algorithm for a convolutional neural network, which automatically transfers objects from one image to another. In this case, the user does not need to select parts of the image or define their boundaries. This is reported by The Next Web.
The editor, called Semantic Soft Segmentation (SSS), divides objects and background into different segments. The system analyzes the color, transparency and texture of the edges of objects. It takes into account the semantic proximity of the pixels: they can belong to two objects simultaneously. As a result, on a new background, the objects look clear and without torn edges. The algorithm processes one image on average in 4 minutes.
In August 2018, the author of the blog, AI Weirdness told about the generative-controversial neural network AttnGAN, which draws images by text description. The problem with the algorithm is that it requires too precisely defined picture parameters and sometimes can not determine the boundaries of objects.
SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019
NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.
Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.
Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.
To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.