# Scene Graph to Image Generation with Contextualized Object Layout Refinement

Source: [Scene Graph to Image Generation with Contextualized Object Layout Refinement](<https://www.sota2.com/research/paper/68fa6da51e209131cea3b1fd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:39:21.820Z

Authors: Maor Ivgi, Yaniv Benny, Avichai Ben-David, Jonathan Berant, Lior Wolf

Published: 2020-09-23T06:27:54.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.10939>)

[PDF](<https://arxiv.org/pdf/2009.10939.pdf>)