Image inpainting is an important research direction in the study of computer vision, and is
widely used in image editing and photo inpainting etc. Traditional image inpainting …

Image is known as one of the communication tools between humans. With the development
and availability of digital devices such as cameras and cell phones, taking images has …

How does one adapt a pre-trained visual model to novel downstream tasks without task-
specific finetuning or any model modification? Inspired by prompting in NLP, this paper …

Recent studies have shown the importance of modeling long-range interactions in the
inpainting problem. To achieve this goal, existing approaches exploit either standalone …

Modern image inpainting systems, despite the significant progress, often struggle with mask
selection and holes filling. Based on Segment-Anything Model (SAM), we make the first …

Image inpainting has been widely exploited in the field of computer vision and image
processing. The main purpose of image inpainting is to produce visually plausible structure …

Motivated by the success of Transformers in natural language processing (NLP) tasks, there
exist some attempts (eg, ViT and DeiT) to apply Transformers to the vision domain. However …

We propose PD-GAN, a probabilistic diverse GAN forimage inpainting. Given an input image
with arbitrary holeregions, PD-GAN produces multiple inpainting results withdiverse and …

Existing inpainting methods have achieved promising performance for recovering regular or
small image defects. However, filling in large continuous holes remains difficult due to the …

Given an incomplete image without additional constraint, image inpainting natively allows
for multiple solutions as long as they appear plausible. Recently, multiple-solution inpainting …