Chajin Shin, Taeoh Kim, Sangjin Lee, Sangyoun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Deep-learning-based image inpainting algorithms have shown great performance via powerful learned priors from numerous external natural images. However, they show unpleasant results for test images whose distributions are far from those of the training images because their models are biased toward the training images. In this paper, we propose a simple image inpainting algorithm with test-time adaptation named AdaFill. Given a single out-of-distributed test image, our goal is to complete hole region more naturally than the pre-trained inpainting models. To achieve this goal, we treat the remaining valid regions of the test image as an another training cue because natural images have strong internal similarities. From this test-time adaptation, our network can exploit externally learned image priors from the pre-trained features as well as the internal priors of the test image explicitly. The experimental results show that AdaFill outperforms other models on various out-of-distribution test images. Furthermore, the model named ZeroFill, which is not pre-trained also outperforms the pre-trained models sometimes.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781665441155
Publication statusPublished - 2021
Event2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: 2021 Sept 192021 Sept 22

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Conference2021 IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States

Bibliographical note

Funding Information:
Acknowledgement. This research was supported by RD program for Advanced Integrated-intelligence for Identification (AIID) through the National Research Foundation of KOREA(NRF) funded by Ministry of Science and ICT (NRF-2018M3E3A1057289).

Publisher Copyright:
© 2021 IEEE

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'TEST-TIME ADAPTATION FOR OUT-OF-DISTRIBUTED IMAGE INPAINTING'. Together they form a unique fingerprint.

Cite this