AesCrop: Aesthetic-driven Cropping Guided by Composition
This work addresses the need for visually appealing image cropping in applications like view recommendation and thumbnail generation, though it is incremental as it builds on existing hybrid approaches by adding composition guidance.
The paper tackled the problem of aesthetic-driven image cropping by introducing AesCrop, a composition-aware hybrid model that integrates a VMamba encoder with a novel Mamba Composition Attention Bias (MCAB) and transformer decoder, resulting in outperforming current state-of-the-art methods with superior quantitative metrics and qualitatively more pleasing crops.
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.