Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images

Blind Image Decomposition

“…BIDeN is based on the framework of GANs (Generative Adversarial Networks) [24], and we explore some critical design choices of BIDeN to present a strong model. Designed for a more challenging BID setting, BIDeN still outperforms the current state-of-the-art image decomposition model [84] and shows competitive results compared to models designed for specific tasks. Together, our proposed BID task, our proposed method BIDeN, our constructed benchmark datasets, and our comprehensive results and ablations form a solid foundation for the future study of this challenging topic.…”

“…Deep Generative Priors [36] employs a likelihood-based generative model as a prior to perform the image decomposition task. Deep Adversarial Decomposition (DAD) [84] purposed a unified framework for image decomposition by employing three discriminators. A crossroad L1 loss is introduced to support pixel-wise supervision when domain information is unknown.…”

“…Experiments and results. We compare BIDeN to Double-DIP [21] and DAD [84]. DAD is trained on the first two domains (Fruit, Animal) with mixed input only.…”

“…Various computer vision and computer graphics tasks [21,84,38,42,25,36,27,1,13] can be viewed as image decomposition, which aims to separate a superimposed image into distinct components with only a single observation. For example, foreground/background segmentation [14,62,2,48] aims at decomposing a holistic image into foreground objects and background stuff.…”

“…Vanilla image decomposition tasks come with a fixed and known number of source components, and the number is most often set to two [21,84,38,42,25,77,41,27,4,45,11,17,16,80]. Such a setting does capture some basic realworld cases.…”