Image Super-Resolution
69개 벤치마크 · 논문 1,814편 · 이 태스크의 논문 보기 →
Benchmarks
Set14 - 4x upscaling
BSD100 - 4x upscaling
Urban100 - 4x upscaling
Manga109 - 4x upscaling
Set5 - 2x upscaling
Set14 - 2x upscaling
Set5 - 3x upscaling
BSD100 - 2x upscaling
Urban100 - 2x upscaling
Set14 - 3x upscaling
Urban100 - 3x upscaling
BSD100 - 3x upscaling
DIV2K val - 4x upscaling
Manga109 - 2x upscaling
Manga109 - 3x upscaling
Set5 - 4x upscaling
IXI
Set5 - 8x upscaling
Set14 - 8x upscaling
VggFace2 - 8x upscaling
WebFace - 8x upscaling
BSD100 - 8x upscaling
ImageNet
CelebA
Manga109 - 8x upscaling
Urban100 - 8x upscaling
CelebA-HQ 128x128
DIV8K val - 16x upscaling
General100 - 4x upscaling
PIRM-test
2x upscaling
3x upscaling
4x upscaling
B100 - 2x upscaling
B100 - 3x upscaling
B100 - 4x upscaling
BSDS100 - 2x upscaling
CUFED5 - 4x upscaling
DIV2K val - 8x upscaling
Sun80 - 4x upscaling
BSD100 - 16x upscaling
BSD200 - 2x upscaling
BSDS100 - 4x upscaling
BSDS100 - 8x upscaling
Celeb-HQ 4x upscaling
Chikusei Dataset
EPFL NIR-VIS
Manga109 - 16x upscaling
Set14
Set5 - 5x upscaling
Set5 - 6x upscaling
ShipSpotting
TextZoom
USR-248 - 4x upscaling
Urban100 - 16x upscaling
WLFW
Most implemented
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Image Super-Resolution Using Deep Convolutional Networks
SinGAN: Learning a Generative Model from a Single Natural Image
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Papers
Learning Spatial-Spectral Refinement and Calibrating Complementary Observations for Hyperspectral Image Super-Resolution
Hyperspectral and multispectral image fusion (HMIF) aims to reconstruct a high-resolution hyperspectral image (HR-HSI) by combining the fine spatial details of a high-resolution multispectral image (HR-MSI) with the rich…
Spectral ReconstructionImage Super-ResolutionSemantic SegmentationUncertainty-Guided Latent Diffusion Models for Faithful Super Resolution
The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realistic images, achieving high fidelity rema…
Image Super-ResolutionSFMformer: A Spatial-Frequency Modulation Transformer for Lightweight Image Super-Resolution
Sparse attention mechanisms, which score all token pairs but propagate only the strongest, now underpin the most efficient Transformers for lightweight image super-resolution. This paper observes that sparsification chan…
Image Super-ResolutionSupervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution
Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the prediction should evolve between the downsampled observation and its fin…
Image Super-ResolutionIR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing
Efficient processing is becoming increasingly important in infrared remote sensing, where satellite constellations produce large volumes of observations under constrained detector resolution, power, and downlink bandwidt…
Multi-Frame Super-ResolutionImage Super-ResolutionRarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution
Continuous diffusion models have become the dominant paradigm for photo-realistic image Super-Resolution (SR), but they typically formulate reconstruction as continuous signal-level denoising and incorporate semantic pri…
Image Super-Resolution