HALO通过分层变换实现更自然的图像重定向，减少视觉失真。
HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations
- 将图像分为显著与非显著区域，分别应用不同变形场。
- 引入感知结构相似性损失，有效降低结构扭曲。
- 在用户偏好上比基线平均提升18.4%，效果领先。
图像重定向旨在改变图像宽高比的同时保持内容与结构完整性，减少视觉伪影。现有方法仍常产生大量伪影，或无法保留原始内容与结构。为此，本文提出可端到端训练的HALO方法。由于人类对图像显著区域的失真更敏感，HALO将输入图像分解为显著与非显著层，并对不同层施加不同的变形场。为进一步减少输出图像中的结构失真，提出感知结构相似性损失，衡量输入与输出间的结构相似性，符合人类感知。在RetargetMe数据集上的定量结果与用户研究均表明，HALO达到当前最优性能，尤其在用户偏好上较基线平均提升18.4%。
原文摘要 · Abstract (English)
Image retargeting aims to change the aspect-ratio of an image while maintaining its content and structure with less visual artifacts. Existing methods still generate many artifacts or fail to maintain original content or structure. To address this, we introduce HALO, an end-to-end trainable solution for image retargeting. Since humans are more sensitive to distortions in salient areas than non-salient areas of an image, HALO decomposes the input image into salient/non-salient layers and applies different wrapping fields to different layers. To further minimize the structure distortion in the output images, we propose perceptual structure similarity loss which measures the structure similarity between input and output images and aligns with human perception. Both quantitative results and a user study on the RetargetMe dataset show that HALO achieves SOTA. Especially, our method achieves an 18.4% higher user preference compared to the baselines on average.
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。