Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-4

Video Inpainting

3260 papers • 126 benchmarks • 313 datasets

The goal of Video Inpainting is to fill in missing regions of a given video sequence with contents that are both spatially and temporally coherent. Video Inpainting, also known as video completion, has many real-world applications such as undesired object removal and video restoration. Source: Deep Flow-Guided Video Inpainting

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-inpainting-4

Trend

Dataset

Best Model

Actions

DAVIS

DAVIS

YouTube-VOS 2018

YouTube-VOS 2018

YouTube-VOS

YouTube-VOS

Libraries

i

Use these libraries to find video-inpainting-4 models and implementations

Datasets

DAVIS

YouTube-VOS 2018

YouTube-VOS 2018

How2Sign

KITTI360-EX

FVI

DEVIL

Subtasks

No subtasks available.

Most implemented papers

Beyond the Field-of-View: Enhancing Scene Visibility and Perception With Clip-Recurrent Transformer

Kaiwei Wang, Kailun Yang, Haowen Shi, Qi Jiang, Xiaoyue Yin•Sun Nov 20 2022

This paper proposes the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety and introduces the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation.

5

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

How2Sign

How2Sign

QST

QST

EgoHOS

VideoRemoval4K

Apolloscape Inpainting

Apolloscape Inpainting

0

Free-Form Video Inpainting With 3D Gated Convolution and Temporal PatchGAN

Winston H. Hsu, Ya-Liang Chang, Zhe Yu Liu, Kuan-Ying Lee•Mon Apr 22 2019

A deep learning based free-form video inpainting model is introduced, with proposed 3D gated convolutions to tackle the uncertainty offree-form masks and a novel Temporal PatchGAN loss to enhance temporal consistency.

205 0

Deep Video Inpainting

Joon-Young Lee, I. Kweon, Dahun Kim, Sanghyun Woo•Sat May 04 2019

This work proposes a novel deep network architecture for fast video inpainting built upon an image-based encoder-decoder model that is designed to collect and refine information from neighbor frames and synthesize still-unknown regions.

222 0

Deep Flow-Guided Video Inpainting

Chen Change Loy, Bolei Zhou, Rui Xu, Xiaoxiao Li•Tue May 07 2019

This work first synthesizes a spatially and temporally coherent optical flow field across video frames using a newly designed Deep Flow Completion network, then uses the synthesized flow fields to guide the propagation of pixels to fill up the missing regions in the video.

253 0

DVI: Depth Guided Video Inpainting for Autonomous Driving

Dingfu Zhou, Ruigang Yang, Sibo Zhang, Miao Liao, Feixiang Lu•Thu Jul 16 2020

An automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud is presented, and it is able to fuse multiple videos through 3D point cloud registration, making it possible to inpaint a target video with multiple source videos.

45 0

Learning Joint Spatial-Temporal Transformations for Video Inpainting

Jianlong Fu, Hongyang Chao, Yanhong Zeng•Sun Jul 19 2020

This paper simultaneously fill missing regions in all input frames by self-attention, and proposes to optimize STTN by a spatial-temporal adversarial loss to show the superiority of the proposed model.

334 0

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

Z. Li, Chunle Guo, Mingg-Ming Cheng, Cheng Lu, Jia Qin•Tue Apr 05 2022

An End-to-End framework for Flow-Guided Video Inpainting (E2 FGVI) through elaborately designed three trainable modules, namely, flow completion, feature propagation, and content hallucination modules that can be Jointly optimized, leading to a more efficient and effective inpainting process.

187 0

Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting

Dong Liu, Kaiwen Zhang, Jialun Peng, Jingjing Fu•Mon Jan 23 2023

This work designs a lightweight flow completion network by using local aggregation and edge loss, and proposes a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows.

18 0

Adding a benchmark result helps the community track progress.

Video Inpainting | State-of-the-Art