Image splice manipulation presents a severe challenge in today's society.
With easy access to image manipulation tools, it is easier than ever to modify
images that can mislead individuals, organizations or society. In this work, a
novel, "Visually Attentive Splice Localization Network with Multi-Domain
Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It
contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE)
that extracts attentional features from the RGB, edge and depth domains. Next,
a "visually attentive downsampler" (VA-DS) is responsible for fusing and
downsampling the multi-domain features. Finally, a novel "visually attentive
multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive
field-based convolutions to upsample attentional features by focussing on
different information scales. Experimental results conducted on the public
benchmark dataset CASIA v2.0 prove the potency of the proposed model. It
comfortably beats the existing state-of-the-arts by achieving an IoU score of
0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.

本研究提出了一种名为 “具有视觉关注的多领域特征提取器和多接受域上采样器的图像拼接定位网络” 的新颖方法，它包含了一种独特的 “具有视觉关注的多领域特征提取器”（VA-MDFE），用于从 RGB、边缘和深度领域提取注意力特征。接下来，负责融合和下采样多领域特征的是 “具有视觉关注的下采样器”（VA-DS）。最后，一种新颖的 “具有视觉关注的多接受域上采样器”（VA-MRFU）模块通过专注于不同的信息尺度，使用基于接受域的多个卷积方法来上采样注意力特征。实验结果在公共基准数据集 CASIA v2.0 上证明了该模型的有效性。相较于现有的最先进方法，它在 IoU 得分达到 0.851，像素 F1 得分达到 0.9195，像素 AUC 得分达到 0.8989，表现优越。