HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations
This addresses image retargeting for applications like responsive design, though it is incremental with a layered approach.
The paper tackles the problem of image retargeting to change aspect ratios while minimizing artifacts and preserving content, achieving state-of-the-art results with an 18.4% higher user preference over baselines.
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.