文献类型：期刊文献

英文题名：Extended Multi-scale Feature Fusion and Balanced Generative Adversarial Network for Image Inpainting under Limited Data

作者：Xiao, Ting[1]; Sun, Minqian[1]; Chen, Haoyuan[2]; Li, Jiaqi[1]; Qiu, Yixing[1]; Wang, Zhe[1]; Lu, Dan[3]

机构：[1] Department of Computer Science and Engineering, East China University of Science and Technology, China; [2] School of Artificial Intelligence, OPtics and ElectroNics, Northwestern Polytechnical University, China; [3] School of Computer Science and Technology, Harbin Engineering University, China

年份：2025

卷号：13553

外文期刊名：Proceedings of SPIE - The International Society for Optical Engineering

收录：EI(收录号：20251318125827)

语种：英文

摘要：Image inpainting has made remarkable progress in recent years due to the availability of sufficient training data. However, when the training data is insufficient, i.e., image inpainting in few-shot regimes, the performance of existing image inpainting methods degrades drastically. Two challenges impede image inpainting under few-shot regimes, adequate information and unstable training. To address the above issues, this paper proposes a new method for image inpainting under limited data. Specifically, an Extended Multi-scale Feature Fusion (EMFF) module is proposed to capture representative contextual information by progressively reducing the number of channels for features with increasing receptive fields, thereby utilizing effective information. Additionally, we leverage a multi-scale discriminator whose cross-layer features are mixed for supplementation to formulate a Balanced Generative Adversarial Network (BGAN) to stabilize the training dynamics. Comprehensive experiments demonstrate the effectiveness of the proposed method. ? 2025 SPIE.