Image Retargetability
This work addresses the need for efficient image adaptation in real-world applications, but it is incremental as it builds on existing content-aware retargeting methods by adding a ranking model.
The paper tackles the problem of automatically retargeting images to different aspect ratios while preserving important content by introducing the concept of image retargetability, which measures how well an image can be processed, and proposes a deep convolutional neural network that learns to rank retargetability, achieving high consistency with human labels.
Real-world applications could benefit from the ability to automatically retarget an image to different aspect ratios and resolutions, while preserving its visually and semantically important content. However, not all images can be equally well processed that way. In this work, we introduce the notion of image retargetability to describe how well a particular image can be handled by content-aware image retargeting. We propose to learn a deep convolutional neural network to rank photo retargetability in which the relative ranking of photo retargetability is directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated retargetability rating problem. To train and analyze this model, we have collected a database which contains retargetability scores and meaningful image attributes assigned by six expert raters. Experiments demonstrate that our unified model can generate retargetability rankings that are highly consistent with human labels. To further validate our model, we show applications of image retargetability in retargeting method selection, retargeting method assessment and photo collage generation.