DeepAI AI Chat
Log In Sign Up

Progressive Temporal Feature Alignment Network for Video Inpainting

by   Xueyan Zou, et al.

Video inpainting aims to fill spatio-temporal "corrupted" regions with plausible content. To achieve this goal, it is necessary to find correspondences from neighbouring frames to faithfully hallucinate the unknown content. Current methods achieve this goal through attention, flow-based warping, or 3D temporal convolution. However, flow-based warping can create artifacts when optical flow is not accurate, while temporal convolution may suffer from spatial misalignment. We propose 'Progressive Temporal Feature Alignment Network', which progressively enriches features extracted from the current frame with the feature warped from neighbouring frames using optical flow. Our approach corrects the spatial misalignment in the temporal feature propagation stage, greatly improving visual quality and temporal consistency of the inpainted videos. Using the proposed architecture, we achieve state-of-the-art performance on the DAVIS and FVI datasets compared to existing deep learning approaches. Code is available at


page 2

page 4

page 5

page 8


Frame-Recurrent Video Inpainting by Robust Optical Flow Inference

In this paper, we present a new inpainting framework for recovering miss...

Temporal Feature Warping for Video Shadow Detection

While single image shadow detection has been improving rapidly in recent...

Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization

Warping-based video stabilizers smooth camera trajectory by constraining...

FlowLens: Seeing Beyond the FoV via Flow-guided Clip-Recurrent Transformer

Limited by hardware cost and system size, camera's Field-of-View (FoV) i...

Flow-Guided Video Inpainting with Scene Templates

We consider the problem of filling in missing spatio-temporal regions of...

Progressive Sparse Local Attention for Video object detection

Transferring image-based object detectors to domain of videos remains a ...

Temporal Interlacing Network

For a long time, the vision community tries to learn the spatio-temporal...