Enhancing Object Coherence in Layout-to-Image Synthesis

arXiv:2311.10522v4 Announce Type: replace
Abstract: Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the objects in a scene. However, it remains challenging to control the object coherence, including semantic coherence (e.g., the cat looks at the flowers or not) and physical coherence (e.g., the hand and the racket should not be misaligned). In this paper, we propose a novel diffusion model with effective …

abstract arxiv control cs.ai cs.cv generate however image image generation object objects semantic synthesis type