AMICO: Amodal Instance Composition
This addresses image composition for applications like object insertion and de-occlusion, but it is incremental as it builds on existing approaches by handling incomplete or coarsely segmented objects.
The paper tackles the problem of compositing imperfect objects onto images by developing modules for shape prediction, content completion, and neural blending, achieving state-of-the-art performance on COCOA and KINS benchmarks.
Image composition aims to blend multiple objects to form a harmonized image. Existing approaches often assume precisely segmented and intact objects. Such assumptions, however, are hard to satisfy in unconstrained scenarios. We present Amodal Instance Composition for compositing imperfect -- potentially incomplete and/or coarsely segmented -- objects onto a target image. We first develop object shape prediction and content completion modules to synthesize the amodal contents. We then propose a neural composition model to blend the objects seamlessly. Our primary technical novelty lies in using separate foreground/background representations and blending mask prediction to alleviate segmentation errors. Our results show state-of-the-art performance on public COCOA and KINS benchmarks and attain favorable visual results across diverse scenes. We demonstrate various image composition applications such as object insertion and de-occlusion.