Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment

• URL: http://arxiv.org/abs/2606.05778v1
• Date: Thu, 04 Jun 2026 07:07:01 GMT
• Title: Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
• Abstract summary: We propose Relative Edit-induced Difference Aesthetic learning (RED-Aes) to simulate the human aesthetic reasoning process.<n>Instead of fitting absolute score distributions, RED-Aes explicitly learns the visual factors that drive aesthetic changes.<n>Experiments demonstrate that RED-Aes achieves state-of-the-art performance on multiple public benchmarks, exhibiting superior generalization capabilities.
• Score: 7.510816222411201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional Image Aesthetic Assessment (IAA) methods mainly rely on regressing absolute Mean Opinion Scores (MOS). However, such a paradigm overlooks the inherently dynamic nature of human aesthetic perception, which relies on subconscious comparison against implicit visual references. Consequently, the lack of causal reasoning regarding aesthetic differences prevents models from learning generalizable aesthetic principles, thus limiting their generalization across diverse scenarios. In this work, we rethink the IAA task and propose Relative Edit-induced Difference Aesthetic learning (RED-Aes), a novel framework that leverages controllable image editing models to simulate the human aesthetic reasoning process. Instead of fitting absolute score distributions, RED-Aes explicitly learns the visual factors that drive aesthetic changes. To support this paradigm, we construct the RED-20k dataset, which comprises editing-based image pairs, quantitative aesthetic differences, and Chain-of-Thought (CoT) reasoning. Furthermore, we introduce a three-stage training strategy guided by a relative ranking consistency reward, optimizing the model solely via relative supervision. Extensive experiments demonstrate that RED-Aes achieves state-of-the-art performance on multiple public benchmarks, exhibiting superior generalization capabilities.

Related papers

• From Concepts to Judgments: Interpretable Image Aesthetic Assessment [6.622808110821698]
  Image aesthetic assessment (IAA) aims to predict the aesthetic quality of images as perceived by humans.<n>We propose an interpretable IAA framework grounded in human-understandable aesthetic concepts.<n>Our method achieves competitive predictive performance while offering transparent, human-understandable aesthetic judgments.
  arXiv  Detail & Related papers  (2026-03-18T13:32:42Z)
• Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks [26.53088863857899]
  Image aesthetic assessment (IAA) has extensive applications in content creation, album management, and recommendation systems.<n>State-of-the-art IAA models are typically designed for coarse-grained evaluation.<n>We propose FGAesQ, a novel IAA framework that learns discriminative aesthetic scores from relative ranks.
  arXiv  Detail & Related papers  (2026-03-04T10:13:27Z)
• Unsupervised Synthetic Image Attribution: Alignment and Disentanglement [55.853285140682665]
  We propose a simple yet effective unsupervised method called Alignment and Disentanglement.<n>Specifically, we begin by performing basic concept alignment using contrastive self-supervised learning.<n>Next, we enhance the model's attribution ability by promoting representation disentanglement with the Infomax loss.
  arXiv  Detail & Related papers  (2026-01-30T07:31:53Z)
• ReasonX: MLLM-Guided Intrinsic Image Decomposition [41.961378846441015]
  Intrinsic image decomposition aims to separate images into physical components such as albedo, depth, normals, and illumination.<n>We propose ReasonX, a novel framework that leverages a large language model (MLLM) as a perceptual judge providing relative intrinsic comparisons.<n>Our framework aligns conditional intrinsic predictors by rewarding agreement between the judge's assessments and analytically derived relations from the model's outputs.
  arXiv  Detail & Related papers  (2025-12-03T19:44:07Z)
• Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization [63.169050703903515]
  We propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL)<n>Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data.<n>Experiments demonstrate that Aes-R1 improves the backbone's average PLCC/SRCC by 47.9%/34.8%.
  arXiv  Detail & Related papers  (2025-09-26T04:55:00Z)
• MiCo: Multi-image Contrast for Reinforcement Visual Reasoning [72.81576836419373]
  Chain-of-Thought (CoT) reasoning can be used to link visual cues across multiple images.<n>We adapt rule-based reinforcement learning for Vision-Language Models (VLMs)<n>Our method achieves significant improvements on multi-image reasoning benchmarks and shows strong performance on general vision tasks.
  arXiv  Detail & Related papers  (2025-06-27T17:59:27Z)
• On the Role of Individual Differences in Current Approaches to Computational Image Aesthetics [38.85583529536269]
  Image assessment (IAA) evaluates image aesthetics, a task complicated by image diversity and user subjectivity.<n>Current approaches address this in two stages: Generic IAA (GIAA) models estimate mean aesthetic scores, while Personal IAA (PIAA) models adapt GIAA using transfer learning to incorporate user subjectivity.<n>This work establishes a theoretical foundation for IAA, proposing a unified model that encodes individual characteristics in a distributional format for both individual and group assessments.
  arXiv  Detail & Related papers  (2025-02-27T21:01:19Z)
• A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends [67.43992456058541]
  Image restoration (IR) seeks to recover high-quality images from degraded observations caused by a wide range of factors, including noise, blur, compression, and adverse weather.<n>Traditional IR methods have made notable progress by targeting individual degradation types, but their specialization often comes at the cost of generalization.<n>The all-in-one image restoration paradigm has recently emerged, offering a unified framework that adeptly addresses multiple degradation types.
  arXiv  Detail & Related papers  (2024-10-19T11:11:09Z)
• Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms [91.19304518033144]
  We aim to align vision models with human aesthetic standards in a retrieval system. We propose a preference-based reinforcement learning method that fine-tunes the vision models to better align the vision models with human aesthetics.
  arXiv  Detail & Related papers  (2024-06-13T17:59:20Z)
• ALL-E: Aesthetics-guided Low-light Image Enhancement [45.40896781156727]
  We propose a new paradigm, i.e. aesthetics-guided low-light image enhancement (ALL-E) It introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Our results on various benchmarks demonstrate the superiority of ALL-E over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-28T03:34:10Z)
• VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining [53.470662123170555]
  We propose learning image aesthetics from user comments, and exploring vision-language pretraining methods to learn multimodal aesthetic representations. Specifically, we pretrain an image-text encoder-decoder model with image-comment pairs, using contrastive and generative objectives to learn rich and generic aesthetic semantics without human labels. Our results show that our pretrained aesthetic vision-language model outperforms prior works on image aesthetic captioning over the AVA-Captions dataset.
  arXiv  Detail & Related papers  (2023-03-24T23:57:28Z)
• Appearance Consensus Driven Self-Supervised Human Mesh Recovery [67.20942777949793]
  We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images. We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks. The resulting colored mesh prediction opens up the usage of our framework for a variety of appearance-related tasks beyond the pose and shape estimation.
  arXiv  Detail & Related papers  (2020-08-04T05:40:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.