V-LinkNet: Learning Contextual Inpainting Across Latent Space of Generative Adversarial Network
This work addresses image inpainting for computer vision applications, but it appears incremental as it builds on existing generative models with a novel feature transfer mechanism.
The paper tackled the problem of persistent aberrations in image inpainting by developing V-LinkNet, which uses a recursive residual transition layer and dual encoders to transfer high-level features, resulting in better performance on CelebA-HQ and Paris Street View datasets.
Image inpainting is a key technique in image processing task to predict the missing regions and generate realistic images. Given the advancement of existing generative inpainting models with feature extraction, propagation and reconstruction capabilities, there is lack of high-quality feature extraction and transfer mechanisms in deeper layers to tackle persistent aberrations on the generated inpainted regions. Our method, V-LinkNet, develops high-level feature transference to deep level textural context of inpainted regions our work, proposes a novel technique of combining encoders learning through a recursive residual transition layer (RSTL). The RSTL layer easily adapts dual encoders by increasing the unique semantic information through direct communication. By collaborating the dual encoders structure with contextualised feature representation loss function, our system gains the ability to inpaint with high-level features. To reduce biases from random mask-image pairing, we introduce a standard protocol with paired mask-image on the testing set of CelebA-HQ, Paris Street View and Places2 datasets. Our results show V-LinkNet performed better on CelebA-HQ and Paris Street View using this standard protocol. We will share the standard protocol and our codes with the research community upon acceptance of this paper.