SOTAVerified

Image Super-Resolution

Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.

Papers

Showing 10261050 of 1589 papers

TitleStatusHype
Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution0
Context Reasoning Attention Network for Image Super-Resolution0
not-so-big-GAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution0
Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGANCode1
Memory-Efficient Hierarchical Neural Architecture Search for Image RestorationCode1
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
Attention-based Image Upsampling0
Neural Radiance Flow for 4D View Synthesis and Video ProcessingCode1
Learning-Based Quality Assessment for Image Super-Resolution0
Learning Continuous Image Representation with Local Implicit Image FunctionCode2
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution0
Super-resolution Guided Pore Detection for Fingerprint Recognition0
Bayesian Image Reconstruction using Deep Generative ModelsCode1
Hierarchical Residual Attention Network for Single Image Super-ResolutionCode1
Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors0
Learning Spatial Attention for Face Super-ResolutionCode1
GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution0
Pre-Trained Image Processing TransformerCode1
Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images0
Fully Quantized Image Super-Resolution NetworksCode1
Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Images0
Rank-One Network: An Effective Framework for Image RestorationCode1
Multi-Scale Progressive Fusion Learning for Depth Map Super-Resolution0
Interpreting Super-Resolution Networks with Local Attribution Maps0
Cryo-ZSSR: multiple-image super-resolution based on deep internal learning0
Show:102550
← PrevPage 42 of 64Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DRCT-LPSNR29.54Unverified
2HMA†PSNR29.51Unverified
3Hi-IR-LPSNR29.49Unverified
4HAT-LPSNR29.47Unverified
5HAT_FIRPSNR29.44Unverified
6DRCTPSNR29.4Unverified
7HATPSNR29.38Unverified
8CPAT+PSNR29.36Unverified
9SwinFIRPSNR29.36Unverified
10CPATPSNR29.34Unverified
#ModelMetricClaimedVerifiedStatus
1DRCT-LPSNR28.16Unverified
2HMA†PSNR28.13Unverified
3Hi-IR-LPSNR28.13Unverified
4HAT-LPSNR28.09Unverified
5HAT_FIRPSNR28.07Unverified
6CPAT+PSNR28.06Unverified
7DRCTPSNR28.06Unverified
8HATPSNR28.05Unverified
9CPATPSNR28.04Unverified
10SwinFIRPSNR28.03Unverified
#ModelMetricClaimedVerifiedStatus
1Hi-IR-LPSNR28.72Unverified
2DRCT-LPSNR28.7Unverified
3HMA†PSNR28.69Unverified
4HAT-LPSNR28.6Unverified
5HAT_FIRPSNR28.43Unverified
6DRCTPSNR28.4Unverified
7HATPSNR28.37Unverified
8CPAT+PSNR28.33Unverified
9CPATPSNR28.22Unverified
10PFTPSNR28.2Unverified