Diverse inpainting and editing with gan inversion

AB Yildirim, H Pehlivan, BB Bilecen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent inversion methods have shown that real images can be inverted into StyleGAN's
latent space and numerous edits can be achieved on those images thanks to the …

Inst-inpaint: Instructing to remove objects with diffusion models

AB Yildirim, V Baday, E Erdem, A Erdem… - arXiv preprint arXiv …, 2023 - arxiv.org
Image inpainting task refers to erasing unwanted pixels from images and filling them in a
semantically consistent and realistic way. Traditionally, the pixels that are wished to be …

Deficiency-aware masked transformer for video inpainting

Y Yu, H Fan, L Zhang - arXiv preprint arXiv:2307.08629, 2023 - arxiv.org
Recent video inpainting methods have made remarkable progress by utilizing explicit
guidance, such as optical flow, to propagate cross-frame pixels. However, there are cases …

Deep learning-based image and video inpainting: A survey

W Quan, J Chen, Y Liu, DM Yan, P Wonka - International Journal of …, 2024 - Springer
Image and video inpainting is a classic problem in computer vision and computer graphics,
aiming to fill in the plausible and realistic content in the missing areas of images and videos …

An Improved Face Image Restoration Method Based on Denoising Diffusion Probabilistic Models

Y Pang, J Mao, L He, H Lin, Z Qiang - IEEE Access, 2024 - ieeexplore.ieee.org
Image restoration is a crucial task in computer vision, aiming to fill in missing areas within an
image to restore its integrity. Traditional methods fall short when dealing with intricate facial …

Flow-guided diffusion for video inpainting

B Gu, Y Yu, H Fan, L Zhang - arXiv preprint arXiv:2311.15368, 2023 - arxiv.org
Video inpainting has been challenged by complex scenarios like large movements and low-
light conditions. Current methods, including emerging diffusion models, face limitations in …

Magic: Multi-modality guided image completion

Y Yu, H Wang, T Luo, H Fan, L Zhang - arXiv preprint arXiv:2305.11818, 2023 - arxiv.org
Vanilla image completion approaches exhibit sensitivity to large missing regions, attributed
to the limited availability of reference information for plausible generation. To mitigate this …

Dynamic context-driven progressive image inpainting with auxiliary generative units

Z Wang, K Li, J Peng - The Visual Computer, 2024 - Springer
Image inpainting aims to restore missing or damaged regions of an image with plausible
visual content. Most existing methods always face challenges when dealing with large hole …

[HTML][HTML] Improved medical image inpainting using automatic multi-task learning driven deep learning approach

PL Rakibe, PD Patil - e-Prime-Advances in Electrical Engineering …, 2024 - Elsevier
Distorted medical images can drastically reduce diagnosis accuracy using computer-aided
diagnostic (CAD) systems. The objective of medical image classification is to improve …

SwapInpaint2: Towards high structural consistency in identity-guided inpainting via background-preserving GAN inversion

H Li, Y Zhang, W Wang, S Zhang, S Zhang - Pattern Recognition, 2025 - Elsevier
In this work, we propose SwapInpaint2 to enhance the naturalness of identity-guided face
inpainting. The previous version, SwapInpaint, relied on a generic inpainting model for …