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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 41–50 of 130 papers

Title	Date	Tasks	Status	Hype	Score
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer	Nov 21, 2022	Autonomous Vehiclesobject-detection	CodeCode Available	1	5
INR-V: A Continuous Representation Space for Video-based Generative Tasks	Oct 29, 2022	Video GenerationVideo Inpainting	CodeCode Available	1	5
A Temporally-Aware Interpolation Network for Video Frame Inpainting	Mar 20, 2018	DecoderPrediction	CodeCode Available	0	5
CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting	Jan 1, 2023	Object TrackingVideo Inpainting	CodeCode Available	0	5
Deep Video Inpainting Guided by Audio-Visual Self-Supervision	Oct 11, 2023	audio-visual learningVideo Inpainting	CodeCode Available	0	5
Deep Video Inpainting	May 5, 2019	DecoderImage Inpainting	CodeCode Available	0	5
An Internal Learning Approach to Video Inpainting	Sep 17, 2019	Optical Flow EstimationVideo Inpainting	CodeCode Available	0	5
Deep Flow-Guided Video Inpainting	May 8, 2019	One-shot visual object segmentationOptical Flow Estimation	CodeCode Available	0	5
Fast and Accurate Tensor Completion with Total Variation Regularized Tensor Trains	Apr 17, 2018	Video Inpainting	CodeCode Available	0	5
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion	Oct 10, 2024	Denoisingparameter-efficient fine-tuning	CodeCode Available	0	5

Show:10 25 50

← PrevPage 5 of 13Next →

All datasets DAVIS YouTube-VOS 2018 HQVI (240p)HQVI (480p)HQVI (2K)YouTube-VOS How2Sign

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DMT	PSNR	33.82	—	Unverified
2	E2FGVI	PSNR	33.01	—	Unverified
3	FuseFormer	PSNR	32.54	—	Unverified
4	FGVC	PSNR	30.8	—	Unverified
5	STTN	PSNR	30.67	—	Unverified
6	CAP	PSNR	30.28	—	Unverified
7	VINet	PSNR	28.96	—	Unverified
8	DFVI	PSNR	28.81	—	Unverified
9	LGTSM	PSNR	28.57	—	Unverified
10	FGT++	LPIPS (object)	0.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ProPainter	PSNR	34.43	—	Unverified
2	DMT	PSNR	34.27	—	Unverified
3	E2FGVI	PSNR	33.71	—	Unverified
4	FuseFormer	PSNR	33.29	—	Unverified
5	STTN	PSNR	32.34	—	Unverified
6	CAP	PSNR	31.58	—	Unverified
7	LGTSM	PSNR	29.74	—	Unverified
8	FGVC	PSNR	29.67	—	Unverified
9	VINet	PSNR	29.2	—	Unverified
10	DFVI	PSNR	29.16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STTN	LPIPS	0.05	—	Unverified
2	FuseFormer	LPIPS	0.05	—	Unverified
3	FGVC	LPIPS	0.04	—	Unverified
4	E2FGVI	LPIPS	0.04	—	Unverified
5	RGVI w/o Ref.	LPIPS	0.04	—	Unverified
6	ProPainter	LPIPS	0.04	—	Unverified
7	RGVI	LPIPS	0.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ProPainter	LPIPS	0.05	—	Unverified
2	RGVI w/o Ref.	LPIPS	0.04	—	Unverified
3	FGVC	LPIPS	0.04	—	Unverified
4	RGVI	LPIPS	0.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RGVI w/o Ref.	LPIPS	0.04	—	Unverified
2	RGVI	LPIPS	0.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FGT++	LPIPS	0.03	—	Unverified
2	FGT++*	LPIPS	0.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	INR-V	L1 error	4.51	—	Unverified