Wish You Were Here: Context-Aware Human Generation
This addresses the need for realistic human insertion in images for applications like photo editing or virtual reality, though it appears incremental as it builds on existing pose transfer and generation methods.
The paper tackles the problem of photorealistically inserting humans into existing images while respecting semantic context, achieving convincing high-resolution outputs and state-of-the-art results in pose transfer benchmarks.
We present a novel method for inserting objects, specifically humans, into existing images, such that they blend in a photorealistic manner, while respecting the semantic context of the scene. Our method involves three subnetworks: the first generates the semantic map of the new person, given the pose of the other persons in the scene and an optional bounding box specification. The second network renders the pixels of the novel person and its blending mask, based on specifications in the form of multiple appearance components. A third network refines the generated face in order to match those of the target person. Our experiments present convincing high-resolution outputs in this novel and challenging application domain. In addition, the three networks are evaluated individually, demonstrating for example, state of the art results in pose transfer benchmarks.