• repositories
• Datasets
• papers
  • Non-DL based approach
  • DL based approach
    • 2014-2016
    • 2017
    • 2018
    • 2019
    • 2020
    • 2021
    • 2022
    • 2023
    • 2024
    • 2025
• Super Resolution workshop papers
• Super Resolution survey

Awesome-Super-Resolution（in progress）

Collect some super-resolution related papers, data and repositories.

papers

DL based approach

Note this table is referenced from here

2025

More years papers, plase check Quick navigation

Title	Model	Published	Code	Keywords
CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution	CLIP-SR	arxiv
Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution	DPI	AAAI25	code
StructSR: Refuse Spurious Details in Real-World Image Super-Resolution	StructSR	AAAI25	code
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution	GSASR	arxiv	code
BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution	BF-STVSR	arxiv
Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution	ASID	AAAI25	code
Visual Autoregressive Modeling for Image Super-Resolution	VARSR	ICML 2025	code
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution	BiMaCoSR	ICML 2025	code
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation	FluxSR	ICML 2025	code
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors	FAOR	AAAI25	code
Spatial Degradation-Aware and Temporal Consistent Diffusion Model for Compressed Video Super-Resolution	SDATC	arxiv
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution	CondiQuant	arxiv	code
DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution	DifIISR	CVPR25	code
AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning	AutoLUT	CVPR25	code
QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution	QArtSR	arxiv	code
Emulating Self-attention with Convolution for Efficient Image Super-Resolution	ESC	arxiv	code
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution	CATANet	CVPR25	code
AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution	AdaptSR	arxiv
MegaSR: Mining Customized Semantics and Expressive Guidance for Image Super-Resolution	MegaSR	arxiv	code
Dual-domain Modulation Network for Lightweight Image Super-Resolution	DMNet	arxiv
Dynamic Attention-Guided Diffusion for Image Super-Resolution	MegaSR	WACV 2025
Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution		arxiv
Efficient Burst Super-Resolution with One-step Diffusion	E-BSRD	ACCV 2024
IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution	IM-LUT	ICCV 2025
4KAgent: Agentic Any Image to 4K Super-Resolution	4KAgent	arxiv	code
PromptSR: Cascade Prompting for Lightweight Image Super-Resolution	PromptSR	TMM	code
DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution	DAM-VSR	SIGGRAPH 2025	code
VSRM: A Robust Mamba-Based Framework for Video Super-Resolution	VSRM	ICCV 2025
LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning	LightBSR	ICCV 2025	code
SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution	SimpleGVR	arxiv	code
RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought	RealSR-R1	arxiv	code
One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution	DLoRAL	arxiv	code
Omnidirectional Video Super-Resolution using Deep Learning	S3PO	TMI
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution	Adaptive Dropout	CVPR2025	code
Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution	SSIU	TIP	code
MambaVSR: Content-Aware Scanning State Space Model for Video Super-Resolution	MambaVSR	arxiv
DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion Models	DiffFuSR	arxiv	code
FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution	FCA2	arxiv	code
Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales	SbCA	arxiv
LiftVSR: Lifting Image Diffusion to Video Super-Resolution via Hybrid Temporal Modeling with Only 4$\times$RTX 4090s	liftvsr	arxiv	code
Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution		arxiv
DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation	DualX-VSR	arxiv
Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders	TADiSR	arxiv
Joint Video Enhancement with Deblurring, Super-Resolution, and Frame Interpolation Network	DSFN	arxiv
A Survey of Deep Learning Video Super-Resolution		arxiv
One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation	VPD-SR-1	arxiv
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution	scst	CVPR 2025	code
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance	TextSR	arxiv
Instance Data Condensation for Image Super-Resolution	IDC	arxiv
UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space	UltraVSR	arxiv
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment	CoZ	arxiv	code
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution	DOVE	arxiv	code
Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling	TSS	arxiv
Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution	SAMSR	arxiv	code
High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution	AMSR	arxiv	code
EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events	EvEnhancer	CVPR 2025	code
Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution	LRTI-VSR	arxiv	code
GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution	GuideSR	arxiv
DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution	DSPO	arxiv
NTIRE 2025 Challenge on Image Super-Resolution (\times\4): Methods and Results		arxiv
AnyTSR: Any-Scale Thermal Super-Resolution for UAV	AnyTSR	arxiv	code
Event-Enhanced Blurry Video Super-Resolution	Ev-DeblurVSR	AAAI 2025	code
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report		arxiv
PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution	PIDSR	CVPR 2025	code
BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution	BUFF	AAAI 2025
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution	DiT4SR	arxiv	code
Progressive Focused Transformer for Single Image Super-Resolution	PFT-SR	CVPR 2025	code
Burst Image Super-Resolution with Mamba	BurstMamba	arxiv
Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment	SFD	CVPR2025	code
Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model	UPSR	CVPR 2025	code
Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models	LSRNA	CVPR 2025	code
The Power of Context: How Multimodality Improves Image Super-Resolution	MMSR	CVPR 2025	code
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution	FedVSR	arxiv	code
Rethinking Image Evaluation in Super-Resolution		arxiv
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution	QDM	arxiv	code
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models	PURE	arxiv	code
Auto-Encoded Supervision for Perceptual Image Super-Resolution	AESOP	CVPR 2025	code
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior	DC-VSR	SIGGRAPH 2025	code
ZFusion: Efficient Deep Compositional Zero-shot Learning for Blind Image Super-Resolution with Generative Diffusion Prior	ZFusion	ICCV 2025	code
StyleSRN: Scene Text Image Super-Resolution with Text Style Embedding	StyleSRN	ICCV 2025
Fast Image Super-Resolution via Consistency Rectified Flow	FlowSR	ICCV 2025
Outlier-Aware Post-Training Quantization for Image Super-Resolution	-	ICCV 2025
Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework	3DSR	ICCV 2025
Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysis	BurstM	ICCV 2025
DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations	DiffVSR	ICCV 2025	code
PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution	PatchScaler	ICCV 2025	code
Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image	UHipandas	ICCV 2025	code
IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution	IM-LUT	ICCV 2025
LDIP: Long Distance Information Propagation for Video Super-Resolution	LDIP	ICCV 2025
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis	InfGen	ICCV 2025	code
TrustMark: Robust Watermarking and Watermark Removal for Arbitrary Resolution Images	TrustMark	ICCV 2025	code
FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion	FreeScale	ICCV 2025	code
Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution	TFD	ICCV 2025
Emulating Self-attention with Convolution for Efficient Image Super-Resolution	ESC	ICCV 2025
VSRM: A Robust Mamba-Based Framework for Video Super-Resolution	VSRM	ICCV 2025
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution	STAR	ICCV 2025	code
Rethinking the Upsampling Process in Light Field Super-Resolution with Spatial-Epipolar Implicit Image Function	SEIIF	ICCV 2025	code
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training	TVT	ICCV 2025	code
LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning	LightBSR	ICCV 2025	code
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model	DuCos	ICCV 2025	code
NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion	NeurOp-Diff	ICCV 2025	code
Consistency Trajectory Matching for One-Step Generative Super-Resolution	CTMSR	ICCV 2025	code
Adversarial Purification via Super-Resolution and Diffusion	PuriFlow	ICCV 2025
Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution	MDWT	ICCV 2025
ISP2HRNet: Learning to Reconstruct High Resolution Image from Irregularly Sampled Pixels via Hierarchical Gradient Learning	ISP2HRNet	ICCV 2025	code
MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation	MedVSR	ICCV 2025	code
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution	DiT4SR	ICCV 2025	code
Super Resolved Imaging with Adaptive Optics	-	ICCV 2025	code
Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution	GSASR	ICCV 2025	code
Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis	SparseVAR	ICCV 2025	code
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models	PURE	ICCV 2025	code
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring	Griffon v2	ICCV 2025	code
Blind Video Super-Resolution based on Implicit Kernels	BVSR-IK	ICCV 2025	code
When 512×512 is Not Enough: Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution	-	ICIP 2025
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion	Stream-DiffVSR	arXiv	code	diffusion, video, online, efficient, lightweight
Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution	IIS-SR	arXiv		diffusion, image, perceptual, fidelity, reconstruction
Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution	CODSR	arXiv	code
CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videos	CreativeVR	arXiv	code
Zero-shot Adaptation of Stable Diffusion via Plug-in Hierarchical Degradation Representation for Real-World Super-Resolution	PHDRep	arXiv		diffusion, image, perceptual, fidelity, super-resolution
CARD: Correlation Aware Restoration with Diffusion	CARD	arXiv		diffusion, image, denoising, super-resolution
OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution	OmniScaleSR	arXiv	code
FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring	FMA-Net++	arXiv	code	video, super-resolution
PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-Resolution	PGP-DiffSR	arXiv	code
FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution	FRAMER	arXiv	code
Restora-Flow: Mask-Guided Image Restoration with Flow Matching	Restora-Flow	WACV 2026		diffusion, image, perceptual, denoising, super-resolution
MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model	MFmamba	AAAI 2026	code	attention, image, super-resolution, SR
STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution	STCDiT	arXiv	code	diffusion, transformer, video, fidelity, reconstruction
MambaX: Image Super-Resolution with State Predictive Control	MambaX	arXiv		image, online, efficient, reconstruction, super-resolution
One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution	OSD-ISR	arXiv	code
Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features	DGAF-VSR	arXiv		diffusion, video, perceptual, fidelity, PSNR
Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks	ARAS-FSR	arXiv		image, super-resolution, SR
One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models	LUA	arXiv	code
Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution	TPMamba	arXiv		transformer, attention, image, lightweight, super-resolution
Outlier-Aware Post-Training Quantization for Image Super-Resolution	OA-PTQ	arXiv		attention, image, super-resolution, SR
GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?	GLYPH-SR	arxiv		diffusion, GAN, image, perceptual, fidelity
BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation	BasicAVSR	arXiv	code
DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution	DP²O-SR	NeurIPS 2025	code
Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark	AIM 2025	ICCV 2025		GAN, image, efficient, perceptual, PSNR
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution	FlashVSR	arXiv	code	diffusion, attention, video, image, real-time
HeadsUp! High-Fidelity Portrait Image Super-Resolution		arXiv
LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution	LinearSR	arXiv		diffusion, attention, image, efficient, lightweight
UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution	UniMMVSR	arXiv	code
Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds	DA-DiffSR	arXiv		diffusion, SSIM, super-resolution, SR
PocketSR: The Super-Resolution Expert in Your Pocket Mobiles	PocketSR	arXiv		image, online, efficient, lightweight, fidelity
Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution	Pure-Pass	arXiv	code	image, lightweight, reconstruction, super-resolution, SR
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems	NPN	NeurIPS 2025		diffusion, image, fidelity, reconstruction, super-resolution
InfVSR: Breaking Length Limits of Generic Video Super-Resolution	InfVSR	arXiv	code	diffusion, video, efficient, streaming, denoising
NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution	NSARM	arXiv	code
PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution	PatchVSR	CVPR 2025		diffusion, attention, video, fidelity, super-resolution
Asymmetric VAE for One-Step Video Super-Resolution Acceleration	FastVSR	arXiv	code
Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution	OASIS	arXiv	code
Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution	TVQ-RAP	arXiv	code
Consistency Models as Plug-and-Play Priors for Inverse Problems	CM-PnP	arXiv		diffusion, fidelity, reconstruction, super-resolution
OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution	OS-DiffVSR	arXiv		diffusion, video, image, super-resolution, SR
Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution	TFD-SR	arXiv		image, denoising, super-resolution
EatGAN: An Edge-Attention Guided Generative Adversarial Network for Single Image Super-Resolution	EatGAN	arXiv		GAN, attention, image, lightweight, perceptual
Realism Control One-step Diffusion for Real-World Image Super-Resolution	RCOD-SR	AAAI 2026	Link	diffusion, image, perceptual, fidelity, reconstruction
BIR-Adapter: A Low-Complexity Diffusion Model Adapter for Blind Image Restoration	BIR-Adapter	arXiv		diffusion, attention, image, super-resolution
SwinSRGAN: Swin Transformer-based Generative Adversarial Network for High-Fidelity Speech Super-Resolution	SwinSRGAN	arXiv		diffusion, transformer, GAN, CNN, fidelity
WaveHiT-SR: Hierarchical Wavelet Network for Efficient Image Super-Resolution	WaveHiT-SR	arXiv		transformer, attention, image, efficient, super-resolution
CATformer: Contrastive Adversarial Transformer for Image Super-Resolution	CATformer	arXiv		diffusion, transformer, GAN, image, reconstruction
TinySR: Pruning Diffusion for Real-World Image Super-Resolution	TinySR	arXiv		diffusion, attention, image, real-time, lightweight
Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution	TADSR	arXiv	code	diffusion, image, efficient, fidelity, super-resolution
Arbitrary-Scale 3D Gaussian Super-Resolution	Arbi-3DGSR	AAAI 2026	code	real-time, PSNR, super-resolution
RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution	RAGSR	arXiv		diffusion, attention, image, perceptual, super-resolution
SNNSIR: A Simple Spiking Neural Network for Stereo Image Restoration	SNNSIR	arXiv		attention, image, real-time, online, efficient
Large Kernel Modulation Network for Efficient Image Super-Resolution	LKMN	arXiv	code	transformer, CNN, attention, image, efficient
LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution	LKFMixer	arXiv	code	transformer, CNN, attention, image, efficient
Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior	UHD-LISR	arXiv	code	diffusion, image, super-resolution, SR
Fourier-Guided Attention Upsampling for Image Super-Resolution	FGA-SR	arXiv	code	attention, image, efficient, lightweight, fidelity
Trajectory-aware Shifted State Space Models for Online Video Super-Resolution	TS-Mamba	arXiv		video, online, efficient, super-resolution, SR
RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration	RASR	arXiv		diffusion, image, fidelity, PSNR, SR
OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution	OMGSR	arXiv	code
DiTVR: Zero-Shot Diffusion Transformer for Video Restoration	DiTVR	arXiv		diffusion, transformer, attention, video, denoising
Rotation Equivariant Arbitrary-scale Image Super-Resolution	RE-ASISR	arXiv	Link
QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution	QuantVSR	arXiv	code
SpatioTemporal Difference Network for Video Depth Super-Resolution	STDNet	AAAI 2026	code	video, reconstruction, super-resolution