CREward: A Type-Specific Creativity Reward Model

TL;DR

CREward is the first type-specific creativity reward model that evaluates and guides creative image generation across geometry, material, and texture axes, aligning with human perception and enabling diverse applications.

Contribution

This work introduces the first type-specific creativity reward model, CREward, which captures human perception across multiple creativity axes and leverages LVLMs for evaluation and generation tasks.

Findings

LVLMs strongly align with human creativity judgments.

CREward effectively assesses creativity across three axes.

Application of CREward improves creative image generation and evaluation.

Abstract

Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and underwhelming. In this work, we learn the \emph{first type-specific creativity reward model}, coined CREward, which spans three creativity ``axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.