NEURAL PANELKI LOOKBOOK

Digital clothing has a huge potential. Recently, we have been watching a huge new business being created almost from scratch before our eyes. Now 3D clothes are used to visualize products for advertising purposes, create fashion shows, offer people to try on virtual bows on their photos. Perhaps soon we will have the opportunity to introduce digital clothing into AR so that it would sit naturally and you could change it in real time, as it now works with shoes. All these are eco-friendly ways to compete with fast fashion and consumer culture. The less we produce, the less we harm the planet, but so far a person cannot wear only digital. Huge factories and brands will not stop producing "living clothes", at least in the near future. They work according to a rolled-up scheme and the larger the production, the more it looks like a thick, clumsy beast. It is difficult for him to adapt to new trends and implement any innovations.

We live in a three-dimensional world and an ordinary 2D sketch cannot fully convey the author's ideas. Sometimes the designer himself does not fully understand how his creation will look live. Designing products in 3D space helps to understand all the proportions and build patterns (or modify already standard ones) immediately on the spot. Thus, the process of creating a thing is shortened. There is no need to make 3 samples of products anymore. The customer understands what will happen and can immediately see all the color variations. Together with the local production Rosee Knitwear Factory, we have released an experimental drop of knitted accessories (hats, scarves, balaclavas).

We started by building a 3D visualization of the models and exporting the patterns. Comparing the actual size in centimeters in pixels, we got the number of nodules in each product. Our neural network generated images and then we selected those images that fit the concept, specifically degrading their quality so that one pixel was equal to one node.