PulseAugur
EN
LIVE 07:20:04

New model CREward assesses image creativity across geometry, material, and texture

Researchers have developed CREward, a novel model designed to assess creativity in images across three specific dimensions: geometry, material, and texture. This model was trained using human evaluations and large vision-language models (LVLMs), demonstrating a strong alignment with human perception of creativity. CREward can be used for evaluating images, providing explanations for creative assessments, and generating creative samples for design inspiration or guiding AI generation. AI

IMPACT Introduces a new method for evaluating and generating creative visual content, potentially aiding AI-driven design tools.

RANK_REASON This is a research paper describing a new model for assessing creativity in images. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Jiyeon Han, Ali Mahdavi-Amiri, Hao Zhang, Haedong Jeong ·

    CREward: A Type-Specific Creativity Reward Model

    arXiv:2511.19995v2 Announce Type: replace 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-spec…