Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
This work addresses the challenge of making composite images more realistic for applications in computer vision and graphics, representing an incremental improvement in shadow generation.
The paper tackles the problem of generating realistic shadows for inserted foreground objects in composite images, achieving better visual effects and generalization to real composite images through a two-stage network.
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.