AesCrop: Aesthetic-driven Cropping Guided by Composition

• URL: http://arxiv.org/abs/2510.22528v1
• Date: Sun, 26 Oct 2025 04:30:02 GMT
• Title: AesCrop: Aesthetic-driven Cropping Guided by Composition
• Abstract summary: AesCrop is a composition-aware hybrid image-cropping model that integrates a VMamba image encoder, augmented with a novel Mamba Composition Attention Bias (MCAB)<n>MCAB encodes compositional cues into the attention mechanism, directing AesCrop to focus on the most compositionally salient regions.<n>Extensive experiments demonstrate that AesCrop outperforms current state-of-the-art methods, delivering superior quantitative metrics and qualitatively more pleasing crops.
• Score: 4.402109574578595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aesthetic-driven image cropping is crucial for applications like view recommendation and thumbnail generation, where visual appeal significantly impacts user engagement. A key factor in visual appeal is composition--the deliberate arrangement of elements within an image. Some methods have successfully incorporated compositional knowledge through evaluation-based and regression-based paradigms. However, evaluation-based methods lack globality while regression-based methods lack diversity. Recently, hybrid approaches that integrate both paradigms have emerged, bridging the gap between these two to achieve better diversity and globality. Notably, existing hybrid methods do not incorporate photographic composition guidance, a key attribute that defines photographic aesthetics. In this work, we introduce AesCrop, a composition-aware hybrid image-cropping model that integrates a VMamba image encoder, augmented with a novel Mamba Composition Attention Bias (MCAB) and a transformer decoder to perform end-to-end rank-based image cropping, generating multiple crops along with the corresponding quality scores. By explicitly encoding compositional cues into the attention mechanism, MCAB directs AesCrop to focus on the most compositionally salient regions. Extensive experiments demonstrate that AesCrop outperforms current state-of-the-art methods, delivering superior quantitative metrics and qualitatively more pleasing crops.

Related papers

• CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference [8.129228105494434]
  Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping.<n>Previous methods often rely on saliency prediction or retrieval augmentation, ignoring the task's core requirement: a deep understanding of composition and aesthetics.<n>We propose a novel paradigm that reformulates aesthetic cropping as a multimodal reasoning task, aiming to activate the VLM's analytical and comprehension capabilities in aesthetics.
  arXiv  Detail & Related papers  (2026-05-09T10:21:51Z)
• AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing [78.6161238980415]
  AttDiff-GAN is a hybrid framework that combines GAN-based attribute manipulation with diffusion-based image generation.<n>We show that the proposed method achieves more accurate facial attribute editing and better preservation of non-target attributes than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-23T05:05:46Z)
• VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis [23.50866105623598]
  We propose a diffusion-based framework that synthesizes a single, coherent object by integrating two input images at both noise and latent levels.<n>Our method outperforms strong baselines in visual quality, semantic consistency, and human-rated creativity.
  arXiv  Detail & Related papers  (2025-09-28T03:17:58Z)
• FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus [10.615833390806486]
  Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization.<n>We present FocusDPO, a framework that adaptively identifies focus regions based on dynamic semantic correspondence and supervision image complexity.
  arXiv  Detail & Related papers  (2025-09-01T07:06:36Z)
• CDG-MAE: Learning Correspondences from Diffusion Generated Views [19.24402848656637]
  CDG-MAE is a novel MAE-based self-supervised method that uses diverse synthetic views generated from static images.<n>These generated views exhibit substantial changes in pose and perspective, providing a rich training signal.
  arXiv  Detail & Related papers  (2025-06-22T20:40:11Z)
• IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation [70.8833857249951]
  IterComp is a novel framework that aggregates composition-aware model preferences from multiple models.<n>We propose an iterative feedback learning method to enhance compositionality in a closed-loop manner.<n>IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation.
  arXiv  Detail & Related papers  (2024-10-09T17:59:13Z)
• FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior [50.0535198082903]
  We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. We showcase the potential of utilizing the powerful generative prior inherent in large-scale pre-trained diffusion models to accomplish generic image composition.
  arXiv  Detail & Related papers  (2024-07-06T03:35:43Z)
• Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model [80.61157097223058]
  A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. We introduce an innovative inter-class data augmentation method known as Diff-Mix, which enriches the dataset by performing image translations between classes.
  arXiv  Detail & Related papers  (2024-03-28T17:23:45Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• Single Stage Virtual Try-on via Deformable Attention Flows [51.70606454288168]
  Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image. We develop a novel Deformable Attention Flow (DAFlow) which applies the deformable attention scheme to multi-flow estimation. Our proposed method achieves state-of-the-art performance both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-07-19T10:01:31Z)
• Adversarial Image Composition with Auxiliary Illumination [53.89445873577062]
  We propose an Adversarial Image Composition Net (AIC-Net) that achieves realistic image composition. A novel branched generation mechanism is proposed, which disentangles the generation of shadows and the transfer of foreground styles. Experiments on pedestrian and car composition tasks show that the proposed AIC-Net achieves superior composition performance.
  arXiv  Detail & Related papers  (2020-09-17T12:58:16Z)

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.