SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2861–2870 of 3874 papers

TitleStatusHype
Towards a Sampling Theory for Implicit Neural Representations—0
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence—0
Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images—0
Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation—0
Towards Realistic Data Generation for Real-World Super-Resolution—0
Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization—0
Towards Real-world Video Face Restoration: A New Benchmark—0
Towards Robust Drone Vision in the Wild—0
Towards the Automation of Deep Image Prior—0
Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric—0
Show:102550
← PrevPage 287 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified