SOTAVerified

Video Inpainting

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 130 papers

TitleStatusHype
Video Virtual Try-on with Conditional Diffusion Transformer Inpainter—0
Let Your Video Listen to Your Music!—0
VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Models—0
Follow-Your-Creation: Empowering 4D Creation through Video Inpainting—0
DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds—0
Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios—0
DiTPainter: Efficient Video Inpainting with Diffusion Transformers—0
Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting—0
GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting—0
VIP: Video Inpainting Pipeline for Real World Human Removal—0
Show:102550
← PrevPage 1 of 13Next →
All datasetsDAVISYouTube-VOS 2018HQVI (240p)HQVI (480p)HQVI (2K)YouTube-VOSHow2Sign

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DMTPSNR33.82—Unverified
2E2FGVIPSNR33.01—Unverified
3FuseFormerPSNR32.54—Unverified
4FGVCPSNR30.8—Unverified
5STTNPSNR30.67—Unverified
6CAPPSNR30.28—Unverified
7VINetPSNR28.96—Unverified
8DFVIPSNR28.81—Unverified
9LGTSMPSNR28.57—Unverified
10FGT++LPIPS (object)0.04—Unverified