Original scientific paper
https://doi.org/10.24138/jcomss-2025-0247
A W-Structured Encoder-Decoder Network Combining Swin Transformer and CNN for Image Inpainting Forensics
Mohamed Fathy Mohamed
orcid.org/0009-0008-9701-7533
; Helwan University, Cairo, Egypt
*
Hala Abdel-Galil ElSayed
; Helwan University, Cairo, Egypt
Soha Ahmed Ehssan Aly
; Helwan University, Cairo, Egypt
* Corresponding author.
Abstract
Image inpainting is rapidly developing currently
due to the progress of deep learning techniques and generative
models. This has led to a loss of integrity in digital content, where
inpainting techniques enable the production of highly realistic
altered images that cannot be easily detected. To address these
risks, this paper proposes a new deep learning–based image
inpainting forensic network called W2SC-Net. The proposed
architecture adopts a W-structured encoder-decoder design that
integrates the Swin transformers with convolutional neural networks
(CNNs). Specifically, the encoder block consists of two parallel
streams to effectively extract both local textures and global
contextual information. The decoder block is connected with
the downsampling stages to enable accurate reconstruction. In
addition, a high-pass filtered enhancement block is employed to
highlight inpainting artifacts. Extensive experiments demonstrate
not only the high detection performance of the proposed model
but also its strong generalization capability. Although it was
trained only on one inpainting method, it can accurately detect
image manipulations across ten inpainting methods and diverse
image datasets. Moreover, the W2SC-Net’s robustness against
anti-forensics attacks is further improved by introducing an
additional training process. Finally, the W2SC-Net outperforms
state-of-the-art forensic approaches in terms of F1-score and AUC
evaluation metrics.
Keywords
Deep Learning; Image Inpainting Forensics; Inpainting Detection; Convolutional Neural Network (CNN); Swin Transformer; Dual-Stream Feature Extraction
Hrčak ID:
348548
URI
Publication date:
31.3.2026.
Visits: 0 *