Scene Graph to Image Generation with Contextualized Object Layout Refinement

Autor:	Ivgi, Maor, Benny, Yaniv, Ben-David, Avichai, Berant, Jonathan, Wolf, Lior
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Appeared at IEEE International Conference in Image Processing (ICIP) 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2009.10939 Zobrazit plný text záznamu View this record from Arxiv