During recent years, people started to produce more and more trash, polluting the planet. Even with continuing recycling, there is one important issue – trash on streets. It can be in already packaged bags or individual wrappers and bottles on the group, with some of it later being in the waters of Earth. The idea of the project is to create a trash detector using computer vision networks that can be used in 2 ways. Firstly, it can be integrated with already installed security cameras and have some software for trash collectors to use, so they would know where the trash is. Second more improved strategy is to create an automated robot which would collect the trash.
Synthesizing a novel view from different angles is an interest in many fields like VR, video enhancement, games, etc. However, this process has some limitations when given an image of an object from an unrecognizable angle. The proposed method combines image-to-image translation with stable diffusion by giving text as an additional parameter