Bridging Global Context Interactions for High-Fidelity Pluralistic Image Completion

Chuanxia Zheng, Guoxian Song, Tat-Jen Cham, Jianfei Cai, Linjie Luo, Dinh Phung

Abstract

We introduce PICFormer, a novel framework for P luralistic I mage C ompletion using a trans Former based architecture, that achieves both high quality and diversity at a much faster inference speed. Our key contribution is to introduce a code-shared codebook learning using a restrictive CNN on small and non-overlapping receptive fields (RFs) for the local visible token representation. This results in a compact yet expressive discrete representation, facilitating efficient modeling of global visible context relations by the transformer. Unlike the prevailing autoregressive approaches, we proposed to sample all tokens simultaneously, leading to more than 100× faster inference speed. To enhance appearance consistency between visible and generated regions, we further propose a novel attention-aware layer (AAL), designed to better exploit distantly related high-frequency features. Through extensive experiments, we demonstrate that the PICFormer efficiently learns semantically-rich discrete codes, resulting in significantly improved image quality. Moreover, our diverse image completion framework surpasses State-of-the-Art methods on multiple image completion datasets.
BibTeX
@article{zheng2024bridging,
  author = {Chuanxia Zheng and Guoxian Song and Tat-Jen Cham and Jianfei Cai and Linjie Luo and Dinh Phung},
  title = {{Bridging Global Context Interactions for High-Fidelity Pluralistic Image Completion}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2024},
  doi = {10.1109/tpami.2024.3403695},
}

Loading related content...

Figure