https://portal.paperswithcode.com/task/video-inpainting
Find 43 papers with code and 4 benchmarks on video inpainting, a task of filling in missing regions of a video sequence. Explore 12 datasets and the most implemented papers on video inpainting for various applications.

https://runwayml.com/inpainting/
Runway is a browser-based video production studio that lets you remove any object from any video with just a few brush strokes. Learn how to use the Inpainting Magic Tool and try Runway for free.

https://github.com/topics/video-inpainting
To associate your repository with the video-inpainting topic, visit your repo's landing page and select "manage topics." GitHub is where people build software. More than 100 million people use GitHub to discover, fork, and contribute to over 420 million projects.

https://nbei.github.io/video-inpainting.html
A novel approach to fill in missing regions of a video by synthesizing a coherent optical flow field and propagating pixels across frames. The paper presents the framework, the network design, the evaluation and the results of the method.

https://paperswithcode.com/paper/deep-video-inpainting
Learn how to fill spatio-temporal holes in a video with a novel deep network architecture that runs in near real-time. Compare the results of the proposed method with other video inpainting algorithms on DAVIS and YouTube-VOS datasets.

https://arxiv.org/abs/2401.17883
Learn about the latest advancements in video inpainting, a process that restores or fills in missing or corrupted portions of video sequences. This paper analyzes major techniques, their theories, applications, and compares their visual quality and computational efficiency.

https://arxiv.org/abs/2401.03395
A comprehensive review of deep learning methods for filling in missing areas of images and videos. The paper covers different inpainting pipelines, architectures, objectives, datasets, metrics, applications, and challenges.

https://towardsdatascience.com/deep-video-inpainting-756e60ddcaaf
Learn how to use deep neural networks to mask unwanted parts of the video and replace them with content that would seamlessly fit into the video. Compare different methods and benchmarks for video inpainting, such as copy and paste, generative models, and optical flow.

https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Deep_Stereo_Video_Inpainting_CVPR_2023_paper.pdf
that single video inpainting needs to achieve, another key challenge for stereo video inpainting is to maintain the stereo consistency between left and right views and hence alleviate the 3D fatigue for viewers. In this paper, we pro-pose a novel deep stereo video inpainting network named SVINet, which is the first attempt for stereo video

https://arxiv.org/abs/1905.01639
A novel deep network architecture for fast video inpainting, which fills spatio-temporal holes with plausible content in a video. The paper is accepted at CVPR 2019 and provides a DOI link for downloading the PDF.

https://ieeexplore.ieee.org/document/10345745
Video inpainting aims to fill in missing regions of a video after any undesired contents are removed from it. This technique can be applied to repair the broken video or edit the video content. In this paper, we propose a depth-guided deep video inpainting network (DGDVI) and demonstrate its effectiveness in processing challenging broken areas crossing multiple depth layers. To achieve our

https://deepai.org/publication/deep-video-inpainting
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting.

https://paperswithcode.com/paper/deep-flow-guided-video-inpainting
Video inpainting, which aims at filling in missing regions of a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel flow-guided video inpainting approach. Rather than filling in the RGB pixels of each frame directly, we consider video

https://zhang-zx.github.io/AVID/
At its core, our model is equipped with effective motion modules and adjustable structure guidance, for fixed-length video inpainting. Building on top of that, we propose a novel Temporal MultiDiffusion sampling pipeline with an middle-frame attention guidance mechanism, facilitating the generation of videos with any desired duration.

https://arxiv.org/pdf/1905.01639
This paper proposes a deep 3D-2D encoder-decoder network for fast and accurate video inpainting. The network collects and refines features from neighbor frames, enforces temporal consistency, and runs in near real-time.

https://tengfei-wang.github.io/Implicit-Internal-Video-Inpainting/index.html
Video Inpainting for Multiple Domains . Most recent video inpainting methods are trained on large video datasets to achieve promising completion performance. Prior internal methods also rely on well-trained and off-the-shelf optical flow estimation networks trained on a target domain. However, the dataset collection process is time-consuming

https://arxiv.org/abs/1905.02884
A novel approach to fill in missing regions of a video using a synthesized optical flow field. The paper presents the method, the evaluation results and the code on arXiv, a preprint server for computer science research.

https://arxiv.org/abs/2311.15368
Video inpainting has been challenged by complex scenarios like large movements and low-light conditions. Current methods, including emerging diffusion models, face limitations in quality and efficiency. This paper introduces the Flow-Guided Diffusion model for Video Inpainting (FGDVI), a novel approach that significantly enhances temporal consistency and inpainting quality via reusing an off

https://arxiv.org/html/2401.03395v1
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. With the advance of deep learning, this problem has achieved significant progress recently. The goal of this paper is to comprehensively review the deep

https://arxiv.org/abs/2406.17628
Deep video inpainting is typically used as malicious manipulation to remove important objects for creating fake videos. It is significant to identify the inpainted regions blindly. This letter proposes a simple yet effective forensic scheme for Video Inpainting LOcalization with ContrAstive Learning (ViLocal). Specifically, a 3D Uniformer encoder is applied to the video noise residual for