"Special Relativity" of Image Aesthetics Assessment: a Preliminary Empirical Perspective

Rui Xie, Anlong Ming, Shuai He, Yi Xiao, Huadong Ma

Abstract:

Image aesthetics assessment (IAA) primarily examines image quality from a user-centric perspective and can be applied to guide various applications, including image capture, recommendation, and enhancement.
The fundamental issue in IAA revolves around the quantification of image aesthetics.
Existing methodologies rely on assigning a scalar (or a distribution) to represent aesthetic value based on conventional practices, which confines this scalar within a specific range and artificially labels it.
However, conventional methods rarely incorporate research on interpretability, particularly lacking systematic responses to the following three fundamental questions:
1) Can aesthetic qualities be quantified?
2) What is the nature of quantifying aesthetics?
3) How can aesthetics be accurately quantified?

In this paper, we present a law called "Special Relativity" of IAA (SR-IAA) that addresses the aforementioned core questions. We have developed a Multi-Attribute IAA Framework (MAINet), which serves as a preliminary validation for SR-IAA within the existing datasets and achieves state-of-the-art (SOTA) performance. Specifically, our metrics on multi-attribute assessment outperform the second-best performance by 8.06% (AADB), 1.67% (PARA), and 2.44% (SPAQ) in terms of SRCC. We anticipate that our research will offer innovative theoretical guidance to the IAA research community. Codes are available in the supplementary material.

Relevance To Conference:

1. This paper primarily investigates the fundamental principles of image aesthetic assessment (IAA) and its preliminary verification. IAA primarily examines image quality from a user-centric perspective.
2. Relevance to multimedia: IAA converts images into scores (number) or comments (text), involving multiple media (image, number, text).
3. Relevance to multimodal: this paper developed a Multi-Attribute IAA Framework for 7 aesthetic Attributes (artifact, composition, color, noiseness, exposure, sharpness and white balance).
4. Contributions to multimedia or multimodal processing: To the best of our knowledge, this study represents the first comprehensive and systematic analysis addressing three fundamental issues in IAA and proposes a law called SR-IAA. To validate this law, we have developed a multi-attribute IAA framework that incorporates modules for automated reference image selection and integration of aesthetic attributes into the comparison process. Experimental results show that our method, guided by our proposed law, outperforms conventional SOTA methods.
5. This paper reviews and references 11 MM/ICME papers within the Multimedia field.

Primary Subject Area: [Experience] Interactions and Quality of Experience

Secondary Subject Area: [Content] Media Interpretation

Submission Number: 2861