Vehicle Image Generation Going Well with the Surroundings

Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Daesik Kim, Nojun Kwak

Abstract: In spite of the advancement of generative models, there have been few studies generating objects in uncontrolled real-world environments. In this paper, we propose an approach for vehicle image generation in real-world scenes. Using a subnetwork based on a precedent work of image completion, our model makes the shape of an object. Details of objects are trained by additional colorization and refinement subnetworks, resulting in a better quality of generated objects. Unlike many other works, our method does not require any segmentation layout but still makes a plausible vehicle in an image. We evaluate our method by using images from Berkeley Deep Drive (BDD) and Cityscape datasets, which are widely used for object detection and image segmentation problems. The adequacy of the generated images by the proposed method has also been evaluated using a widely utilized object detection algorithm and the FID score.