CareCom: Generative Image Composition with Calibrated Reference Features
This work addresses image composition challenges for computer vision applications, presenting an incremental improvement over existing generative models.
The paper tackles the problem of generative image composition by addressing simultaneous detail preservation and foreground pose/view adjustment, achieving improved performance through calibrated reference features as demonstrated on MVImgNet and MureCom datasets.
Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features.