用视觉注意力流动分析照片构图，效果超越现有方法
Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion
- 融合显著性与边缘信息生成视觉注意力流场
- 在PICD数据集上准确率提升超30%，达最新水平
- 自监督特征+简单分类器胜过复杂专用模型
可靠评估摄影构图需具备区分空间布局又对语义内容鲁棒的特征。本文提出基于视觉注意力沿几何结构流动的假设，构建低层表示。引入VFCNet，将显著性与边缘信息融合为梯度向量流（GVF）场，计算双流GVF表示，通过注意力机制整合，并利用DINOv3主干提取多尺度流特征。在PICD基准测试中表现领先（CDA-1: 0.683，CDA-2: 0.629），相较之前最优方法分别提升33.1%和36.1%。此外，仅用自监督DINOv3特征搭配简单分类器，即显著优于更复杂的构图专用模型。代码已开源：https://github.com/ADadras/VFCNet
原文摘要 · Abstract (English)
The reliable computational assessment of photographic composition requires features that are discriminative of spatial layout yet robust to semantic content. This paper proposes a low-level representation grounded in the assumption that composition can be understood as the flow of visual attention across geometric structure. We introduce VFCNet, which fuses saliency and edge information into a gradient vector flow (GVF) field. The model computes dual-stream GVF representations, integrates them via attention, and extracts multi-scale flow features with a DINOv3 backbone. VFCNet achieves state-of-the-art performance on the PICD benchmark (CDA-1: 0.683, CDA-2: 0.629), improving by 33.1\% and 36.1\% over the previous best method. We also show that a simple classifier on self-supervised DINOv3 features substantially outperforms more sophisticated, composition-specialized models. Code is available at https://github.com/ADadras/VFCNet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。