Papers
arxiv:2411.15435

What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation

Published on Nov 23, 2024
Authors:
,
,
,

Abstract

Scene-Bench, a comprehensive benchmark with MegaSG dataset and SGScore metric, evaluates and enhances factual consistency in complex scene generation through iterative refinement using scene graph feedback.

AI-generated summary

While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modeling spatial relationships and object interactions. To fill this gap, we introduce Scene-Bench, a comprehensive benchmark designed to evaluate and enhance the factual consistency in generating natural scenes. Scene-Bench comprises MegaSG, a large-scale dataset of one million images annotated with scene graphs, facilitating the training and fair comparison of models across diverse and complex scenes. Additionally, we propose SGScore, a novel evaluation metric that leverages chain-of-thought reasoning capabilities of multimodal large language models (LLMs) to assess both object presence and relationship accuracy, offering a more effective measure of factual consistency than traditional metrics like FID and CLIPScore. Building upon this evaluation framework, we develop a scene graph feedback pipeline that iteratively refines generated images by identifying and correcting discrepancies between the scene graph and the image. Extensive experiments demonstrate that Scene-Bench provides a more comprehensive and effective evaluation framework compared to existing benchmarks, particularly for complex scene generation. Furthermore, our feedback strategy significantly enhances the factual consistency of image generation models, advancing the field of controllable image generation.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2411.15435 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2411.15435 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.