Semantically Consistent Person Image Generation
This addresses the challenge of context-aware person image generation for computer vision applications, representing an incremental improvement through a multi-step hybrid approach.
The paper tackles the problem of generating realistic person images that blend seamlessly into complex scenes by conditioning position, scale, and appearance on existing scene semantics, achieving semantically coherent results as validated through qualitative and quantitative evaluations.
We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations.