Image datasets generation system for computer vision applications based on photorealistic rendering
Abstract:
In this paper we present an approach to image datasets generation based on photorealistic rendering with controlled parameter randomization of 3d scenes. These datasets can be used, for example, for training artificial intelligence models in computer vision. We describe the architecture of system implementing proposed approach and show examples of applying it to specific problems.
Keywords:
photorealistic rendering, 3d scene generation, computer vision, GPU
