Scene Graph to Image Generation with Contextualized Object Layout Refinement
This work improves image generation from scene graphs, which is important for applications like visual content creation, though it appears incremental in refining layout generation.
The paper tackles the problem of generating images from scene graphs by addressing issues of object overlap and low coverage in intermediate layouts, achieving a 20-point improvement in layout coverage and reducing overlap to negligible amounts.
Generating images from scene graphs is a challenging task that attracted substantial interest recently. Prior works have approached this task by generating an intermediate layout description of the target image. However, the representation of each object in the layout was generated independently, which resulted in high overlap, low coverage, and an overall blurry layout. We propose a novel method that alleviates these issues by generating the entire layout description gradually to improve inter-object dependency. We empirically show on the COCO-STUFF dataset that our approach improves the quality of both the intermediate layout and the final image. Our approach improves the layout coverage by almost 20 points and drops object overlap to negligible amounts.