SOTAVerified

Video Super-Resolution

Video Super-Resolution is a computer vision task that aims to increase the resolution of a video sequence, typically from lower to higher resolutions. The goal is to generate high-resolution video frames from low-resolution input, improving the overall quality of the video.

( Image credit: Detail-revealing Deep Video Super-Resolution )

Papers

Showing 1–10 of 281 papers

TitleStatusHype
Compressed Video Super-Resolution based on Hierarchical Encoding—0
FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-ResolutionCode0
ICME 2025 Grand Challenge on Video Super-Resolution for Video ConferencingCode1
LiftVSR: Lifting Image Diffusion to Video Super-Resolution via Hybrid Temporal Modeling with Only 4RTX 4090s—0
A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-ResolutionCode0
DualX-VSR: Dual Axial SpatialTemporal Transformer for Real-World Video Super-Resolution without Motion Compensation—0
Omnidirectional Video Super-Resolution using Deep Learning—0
A Survey of Deep Learning Video Super-Resolution—0
UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space—0
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionCode2
Show:102550
← PrevPage 1 of 29Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RVRTPSNR29.54—Unverified
2VRTPSNR29.42—Unverified
3BasicVSR++PSNR29.04—Unverified
4FTVSRPSNR28.7—Unverified
5GOVSRPSNR28.41—Unverified
6TTVSRPSNR28.4—Unverified
7IconVSRPSNR28.04—Unverified
8BasicVSRPSNR27.96—Unverified
9RSDNPSNR27.92—Unverified
10EDVRPSNR27.85—Unverified