Generating Object Stamps
This work addresses the challenge of realistic object insertion in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of generating diverse foreground objects and compositing them into background images by proposing a two-stage GAN architecture that separates object shape and texture generation. Results on the COCO dataset show improved overall quality and diversity compared to state-of-the-art object insertion approaches.
We present an algorithm to generate diverse foreground objects and composite them into background images using a GAN architecture. Given an object class, a user-provided bounding box, and a background image, we first use a mask generator to create an object shape, and then use a texture generator to fill the mask such that the texture integrates with the background. By separating the problem of object insertion into these two stages, we show that our model allows us to improve the realism of diverse object generation that also agrees with the provided background image. Our results on the challenging COCO dataset show improved overall quality and diversity compared to state-of-the-art object insertion approaches.