Computational Visual Media


shadow synthesis, deep learning, genera-tive adversarial networks, image synthesis


We introduce ShadowGAN, a generative adversarial network (GAN) for synthesizing shadows for virtual objects inserted in images. Given a target image containing several existing objects with shadows, and an input source object with a specified insertionposition, the network generates a realistic shadow for the source object. The shadow is synthesized by a generator; using the proposed local adversarial and global adversarial discriminators, the synthetic shadow’s appearance is locally realistic in shape, and globally consistent with other objects’ shadows in terms of shadow direction and area. To overcome the lack of training data, we produced training samples based on public 3D models and rendering technology. Experimental results from a user study show that the synthetic shadowed results look natural and authentic.


Tsinghua University Press