paper-with-me

홈 › Papers

Flow-Guided Video Inpainting with Scene Templates

2021-08-29 · ICCV 2021 10 · Dong Lao, Peihao Zhu, Peter Wonka, Ganesh Sundaramoorthi

We consider the problem of filling in missing spatio-temporal regions of a video. We provide a novel flow-based solution by introducing a generative model of images in relation to the scene (without missing regions) and mappings from the scene to images. We use the model to jointly infer the scene template, a 2D representation of the scene, and the mappings. This ensures consistency of the frame-to-frame flows generated to the underlying scene, reducing geometric distortions in flow based inpainting. The template is mapped to the missing regions in the video by a new L2-L1 interpolation scheme, creating crisp inpaintings and reducing common blur and distortion artifacts. We show on two benchmark datasets that our approach out-performs state-of-the-art quantitatively and in user studies.

📄 PDF Abstract BibTeX arXiv:2108.12845

Code (0)

등록된 구현이 없습니다.

Tasks

Video Inpainting

Similar Papers 제목 키워드 기반

Deep Flow-Guided Video Inpainting

2019-05-08 · CVPR 2019 6 · Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy

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…

One-shot visual object segmentationOptical Flow EstimationVideo fixed region InpaintingVideo Inpainting

Flow-Guided Diffusion for Video Inpainting

2023-11-26 · Bohai Gu, Yongsheng Yu, Heng Fan, Libo Zhang

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 introd…

DenoisingImage GenerationOptical Flow EstimationVideo Inpainting

Towards An End-to-End Framework for Flow-Guided Video Inpainting

2022-04-06 · CVPR 2022 1 · Zhen Li, Cheng-Ze Lu, Jianhua Qin, Chun-Le Guo 외

Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-crafted flow-based processes in these me…

HallucinationOptical Flow EstimationSeeing Beyond the VisibleVideo Inpainting

Advanced Video Inpainting Using Optical Flow-Guided Efficient Diffusion

2024-12-01 · Bohai Gu, Hao Luo, Song Guo, Peiran Dong

Recently, diffusion-based methods have achieved great improvements in the video inpainting task. However, these methods still face many challenges, such as maintaining temporal consistency and the time-consuming issue. T…

DenoisingOptical Flow EstimationVideo Inpainting

Error Compensation Framework for Flow-Guided Video Inpainting

2022-07-21 · Jaeyeon Kang, Seoung Wug Oh, Seon Joo Kim

The key to video inpainting is to use correlation information from as many reference frames as possible. Existing flow-based propagation methods split the video synthesis process into multiple steps: flow completion -> p…

Video Inpainting