Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
This work addresses video editing needs such as text removal, offering a solution for handling complex inpainting tasks in videos, though it appears incremental as it builds on existing inpainting methods with specific enhancements.
The paper tackles the problem of free-form video inpainting, which is challenging due to non-repetitive structures and temporal inconsistency, by introducing a model with 3D gated convolutions and a Temporal PatchGAN loss, achieving superior performance on datasets like FaceForensics and their custom FVI dataset.
Free-form video inpainting is a very challenging task that could be widely used for video editing such as text removal. Existing patch-based methods could not handle non-repetitive structures such as faces, while directly applying image-based inpainting models to videos will result in temporal inconsistency (see http://bit.ly/2Fu1n6b ). In this paper, we introduce a deep learn-ing based free-form video inpainting model, with proposed 3D gated convolutions to tackle the uncertainty of free-form masks and a novel Temporal PatchGAN loss to enhance temporal consistency. In addition, we collect videos and design a free-form mask generation algorithm to build the free-form video inpainting (FVI) dataset for training and evaluation of video inpainting models. We demonstrate the benefits of these components and experiments on both the FaceForensics and our FVI dataset suggest that our method is superior to existing ones. Related source code, full-resolution result videos and the FVI dataset could be found on Github https://github.com/amjltc295/Free-Form-Video-Inpainting .