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

Showing 5175 of 130 papers

TitleStatusHype
Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGANCode0
Deep Video InpaintingCode0
Learnable Gated Temporal Shift Module for Deep Video InpaintingCode0
Expression-aware video inpainting for HMD removal in XR applicationsCode0
Onion-Peel Networks for Deep Video CompletionCode0
Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake VideosCode0
A Temporally-Aware Interpolation Network for Video Frame InpaintingCode0
Deep Blind Video Decaptioning by Temporal Aggregation and RecurrenceCode0
Deep Video Inpainting Guided by Audio-Visual Self-SupervisionCode0
Trusted Video Inpainting Localization via Deep Attentive Noise LearningCode0
UVL2: A Unified Framework for Video Tampering Localization0
Video Diffusion Models are Strong Video Inpainter0
Video Inpainting by Jointly Learning Temporal Structure and Spatial Details0
Video Inpainting of Complex Scenes0
VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Models0
Video Virtual Try-on with Conditional Diffusion Transformer Inpainter0
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models0
VIP: Video Inpainting Pipeline for Real World Human Removal0
Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting0
VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal0
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models0
Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios0
Align-and-Attend Network for Globally and Locally Coherent Video Inpainting0
A New Low-Rank Learning Robust Quaternion Tensor Completion Method for Color Video Inpainting Problem and Fast Algorithms0
A Time-Vertex Signal Processing Framework0
Show:102550
← PrevPage 3 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DMTPSNR33.82Unverified
2E2FGVIPSNR33.01Unverified
3FuseFormerPSNR32.54Unverified
4FGVCPSNR30.8Unverified
5STTNPSNR30.67Unverified
6CAPPSNR30.28Unverified
7VINetPSNR28.96Unverified
8DFVIPSNR28.81Unverified
9LGTSMPSNR28.57Unverified
10FGT++LPIPS (object)0.04Unverified
#ModelMetricClaimedVerifiedStatus
1ProPainterPSNR34.43Unverified
2DMTPSNR34.27Unverified
3E2FGVIPSNR33.71Unverified
4FuseFormerPSNR33.29Unverified
5STTNPSNR32.34Unverified
6CAPPSNR31.58Unverified
7LGTSMPSNR29.74Unverified
8FGVCPSNR29.67Unverified
9VINetPSNR29.2Unverified
10DFVIPSNR29.16Unverified
#ModelMetricClaimedVerifiedStatus
1STTNLPIPS0.05Unverified
2FuseFormerLPIPS0.05Unverified
3FGVCLPIPS0.04Unverified
4E2FGVILPIPS0.04Unverified
5RGVI w/o Ref.LPIPS0.04Unverified
6ProPainterLPIPS0.04Unverified
7RGVILPIPS0.03Unverified
#ModelMetricClaimedVerifiedStatus
1ProPainterLPIPS0.05Unverified
2RGVI w/o Ref.LPIPS0.04Unverified
3FGVCLPIPS0.04Unverified
4RGVILPIPS0.03Unverified
#ModelMetricClaimedVerifiedStatus
1RGVI w/o Ref.LPIPS0.04Unverified
2RGVILPIPS0.04Unverified
#ModelMetricClaimedVerifiedStatus
1FGT++LPIPS0.03Unverified
2FGT++*LPIPS0.02Unverified
#ModelMetricClaimedVerifiedStatus
1INR-VL1 error4.51Unverified