Uncertainty-aware image inpainting with adaptive feedback network

Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Gengyun Jia, Yaohui Wang, Xinyuan Chen, Cunjian Chen

Abstract

While most image inpainting methods perform well on small image defects, they still struggle to deliver satisfactory results on large holes due to insufficient image guidance. To address this challenge, this paper proposes an uncertainty-aware adaptive feedback network (U2AFN), which incorporates an adaptive feedback mechanism to refine inpainting regions progressively. U2AFN predicts both an uncertainty map and an inpainting result simultaneously. During each iteration, the adaptive integration feedback block utilizes inpainting pixels with low uncertainty to guide the subsequent learning iteration. This process leads to a gradual reduction in uncertainty and produces more reliable inpainting outcomes. Our approach is extensively evaluated and compared on multiple datasets, demonstrating its superior performance over existing methods. The code is available at: https://codeocean.com/capsule/1901983/tree.
BibTeX
@article{ma2024uncertainty,
  author = {Xin Ma and Xiaoqiang Zhou and Huaibo Huang and Gengyun Jia and Yaohui Wang and Xinyuan Chen and Cunjian Chen},
  title = {{Uncertainty-aware image inpainting with adaptive feedback network}},
  journal = {Expert Systems with Applications},
  year = {2024},
  url = {https://openreview.net/forum?id=A5eNQ2L4I9},
}

Loading related content...

Figure