DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

TL;DR

DEsignBench is a new benchmark for evaluating text-to-image models like DALL-E 3 in authentic visual design scenarios, combining human and GPT-4V evaluations to assess technical and creative design capabilities.

Contribution

We introduce DEsignBench, a comprehensive benchmark for assessing T2I models in design contexts, including a novel automatic evaluation method using GPT-4V.

Findings

DALL-E 3 performs well in image-text alignment and aesthetic quality.

GPT-4V-based evaluation correlates strongly with human judgments.

Design-specific capabilities like layout and color harmony are effectively assessed.

Abstract

We introduce DEsignBench, a text-to-image (T2I) generation benchmark tailored for visual design scenarios. Recent T2I models like DALL-E 3 and others, have demonstrated remarkable capabilities in generating photorealistic images that align closely with textual inputs. While the allure of creating visually captivating images is undeniable, our emphasis extends beyond mere aesthetic pleasure. We aim to investigate the potential of using these powerful models in authentic design contexts. In pursuit of this goal, we develop DEsignBench, which incorporates test samples designed to assess T2I models on both "design technical capability" and "design application scenario." Each of these two dimensions is supported by a diverse set of specific design categories. We explore DALL-E 3 together with other leading T2I models on DEsignBench, resulting in a comprehensive visual gallery for side-by-side comparisons. For DEsignBench benchmarking, we perform human evaluations on generated images in DEsignBench gallery, against the criteria of image-text alignment, visual aesthetic, and design creativity. Our evaluation also considers other specialized design capabilities, including text rendering, layout composition, color harmony, 3D design, and medium style. In addition to human evaluations, we introduce the first automatic image generation evaluator powered by GPT-4V. This evaluator provides ratings that align well with human judgments, while being easily replicable and cost-efficient. A high-resolution version is available at https://github.com/design-bench/design-bench.github.io/raw/main/designbench.pdf?download=