Image Aesthetic Assessment: An Experimental Survey

Abstract

This survey aims at reviewing recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality photos from low-quality ones based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature trying to solve this challenging problem. In this survey, we present a systematic listing of the reviewed approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (dataset characteristics and evaluation metrics). Main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep learning techniques, we systematically evaluate recent deep learning settings that are useful for developing a robust deep model for aesthetic scoring. Experiments are conducted using simple yet solid baselines that are competitive with the current state-of-the-arts. Moreover, we discuss the possibility of manipulating the aesthetics of images through computational approaches. We hope that our survey could serve as a comprehensive reference source for future research on the study of image aesthetic assessment.

References in corpus (2)

• Learning Deep Representation for Face Alignment with Auxiliary Attributes
• Subjective and Objective Quality Assessment of Image: A Survey

Cited by in corpus (14)

• Language Model Crossover: Variation through Few-Shot Prompting
• Composition and Style Attributes Guided Image Aesthetic Assessment
• Consolidated Dataset and Metrics for High-Dynamic-Range Image Quality
• Multi-task convolutional neural network for image aesthetic assessment
• Image Aesthetics Assessment Using Composite Features from off-the-Shelf Deep Models
• Unveiling The Factors of Aesthetic Preferences with Explainable AI
• Exploring to establish an appropriate model for image aesthetic assessment via CNN-based RSRL: An empirical study
• Exploring CNN-based models for image's aesthetic score prediction with using ensemble
• An Experience-based Direct Generation approach to Automatic Image Cropping
• Image Aesthetics Assessment using Multi Channel Convolutional Neural Networks
• Sample-specific repetitive learning for photo aesthetic assessment and highlight region extraction
• Personalised aesthetics with residual adapters
• Assessing aesthetics of generated abstract images using correlation structure
• M2FN: Multi-step Modality Fusion for Advertisement Image Assessment