English

Instance-Aware Image Completion

Computer Vision and Pattern Recognition 2023-05-29 v3 Artificial Intelligence Machine Learning

Abstract

Image completion is a task that aims to fill in the missing region of a masked image with plausible contents. However, existing image completion methods tend to fill in the missing region with the surrounding texture instead of hallucinating a visual instance that is suitable in accordance with the context of the scene. In this work, we propose a novel image completion model, dubbed ImComplete, that hallucinates the missing instance that harmonizes well with - and thus preserves - the original context. ImComplete first adopts a transformer architecture that considers the visible instances and the location of the missing region. Then, ImComplete completes the semantic segmentation masks within the missing region, providing pixel-level semantic and structural guidance. Finally, the image synthesis blocks generate photo-realistic content. We perform a comprehensive evaluation of the results in terms of visual quality (LPIPS and FID) and contextual preservation scores (CLIPscore and object detection accuracy) with COCO-panoptic and Visual Genome datasets. Experimental results show the superiority of ImComplete on various natural images.

Keywords

Cite

@article{arxiv.2210.12350,
  title  = {Instance-Aware Image Completion},
  author = {Jinoh Cho and Minguk Kang and Vibhav Vineet and Jaesik Park},
  journal= {arXiv preprint arXiv:2210.12350},
  year   = {2023}
}

Comments

AI for Content Creation (AI4CC) CVPR workshop, 2023