Region and Object based Panoptic Image Synthesis through Conditional GANs
This addresses a novel task in computer vision for image synthesis, but it is incremental as it builds on existing GAN-based translation methods.
The paper introduces panoptic-level image-to-image translation, which combines semantic style translation and instance transfiguration to generate images from a detailed panoptic perspective, proposing a naive baseline method for this task.
Image-to-image translation is significant to many computer vision and machine learning tasks such as image synthesis and video synthesis. It has primary applications in the graphics editing and animation industries. With the development of generative adversarial networks, a lot of attention has been drawn to image-to-image translation tasks. In this paper, we propose and investigate a novel task named as panoptic-level image-to-image translation and a naive baseline of solving this task. Panoptic-level image translation extends the current image translation task to two separate objectives of semantic style translation (adjust the style of objects to that of different domains) and instance transfiguration (swap between different types of objects). The proposed task generates an image from a complete and detailed panoptic perspective which can enrich the context of real-world vision synthesis. Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it. The proposed baseline consists of the multiple instances sequential translation and semantic-level translation with domain-invariant content code.