Collect some super-resolution related papers, data and repositories.
Note this table is referenced from here
More years papers, plase check Quick navigation
| Title | Model | Published | Code | Keywords |
|---|---|---|---|---|
| Binarized High-Efficiency RAW Video Restoration and Beyond | - | TPAMI | binary neural network, RAW, video, efficient, lightweight, restoration | |
| ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution | ENAF | WACV 2025 | code | CNN, dynamic network, multi-exit, patch fusion, efficient, super-resolution |
| Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration | PCFlow | ECCV 2026 | code | flow matching, perceptual, distortion-perception, efficient, image, restoration |
| Preserve More Details: Mitigating Content Drift in Real-World Image Super-Resolution | - | ACM MM 2026 | diffusion, stable diffusion, real-world, fidelity, image, super-resolution | |
| Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance | - | ACM MM 2026 | multimodal, prompt, pixel-level guidance, all-in-one, image, restoration | |
| Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration | - | ICML 2026 | transformer, deformable, tokenization, degradation-aware, all-in-one, restoration | |
| Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation | - | ECCV 2026 | INR, sinusoidal, recurrent, spectral, efficient, representation | |
| Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-Resolution | Shift-IISR | ACM MM 2026 | code | diffusion, cross-modality, infrared, prior, image, super-resolution |
| The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results | LoViF | ECCV 2026 Workshop | challenge, benchmark, real-world, all-in-one, image, restoration | |
| QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration | QuReC | ACM MM 2026 | code | transformer, query, attention, calibration, all-in-one, restoration |
| NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices | NanoVSR | ECCV 2026 | code | CNN, flow-free, real-time, edge device, video, super-resolution |
| Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset | Live2K | ECCV 2026 | dataset, benchmark, live photos, frame selection, video, enhancement | |
| AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution | AVSR-Diff | ECCV 2026 | code | diffusion, INR, arbitrary-scale, temporal consistency, video, super-resolution |
| SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy | SkelEM | ECCV 2026 | diffusion, self-supervised, microscopy, anisotropic, axial, super-resolution | |
| DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution | DTI | ECCV 2026 | diffusion, generative prior, face, trajectory, video, super-resolution | |
| FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution | FreqOrtho-SR | ECCV 2026 | code | diffusion, frequency, mixture-of-experts, real-world, image, super-resolution |
| Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution | DP-NSL | ECCV 2026 | code | null-space, spline, arbitrary-scale, medical, slice, super-resolution |
| TaskTok: Delving into Task Tokens for Task-driven Image Restoration | TaskTok | ECCV 2026 | code | token, generative prior, task-driven, efficient, image, restoration |
| LogicIR: Logic Gate Networks for Image Restoration | LogicIR | ECCV 2026 | code | logic gate network, lightweight, efficient, inference, image, restoration |
| Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution | FPLIA | ECCV 2026 | code | INR, attention, arbitrary-scale, fidelity, perceptual, super-resolution |
| Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution | LSM | CVPR 2026 | code | linear recurrent unit, state space, semantic modulation, efficient, image, super-resolution |
| EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution | EvTexture++ | TPAMI | code | event camera, recurrent, texture, video, super-resolution |
| Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment | NADB | CVPR 2026 | code | diffusion bridge, noise alignment, image, translation, restoration |
| Expandable, Compressible, Mineable: Open-World Thermal Image Restoration | ECMRNet | ICML 2026 | code | continual learning, open-world, thermal, infrared, all-in-one, restoration |
| Image Restoration via Diffusion Models with Dynamic Resolution | SubDAPS | ICML 2026 | code | diffusion, posterior sampling, dynamic resolution, efficient, image, restoration |
| Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement | SEGD | CVPR 2026 | code | structural entropy, benchmark, thermal infrared, all-in-one, image, enhancement |
| Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling | Ada-RefSR | ICLR2026 | code | diffusion, one-step, reference-based, attention, image, super-resolution |
| LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion | LiveMoments | ICLR 2026 | code | diffusion, flow-matching, reference-based, image, restoration, 4K |
| Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models | E-Bridge | arxiv | code | diffusion, bridge, image, restoration, one-step, FLUX |
| SAT: Selective Aggregation Transformer for Image Super-Resolution | SAT | CVPR 2026 | code | transformer, attention, image, efficient, reconstruction, super-resolution |
| DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping | DRIFT | CVPR 2026 | GAN, NAFNet, image, multi-frame, denoising, super-resolution | |
| VOSR: A Vision-Only Generative Model for Image Super-Resolution | VOSR | CVPR 2026 | code | diffusion, DiT, DINOv2, distillation, one-step, super-resolution |
| The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report | NTIRE | CVPR 2026 | CNN, distillation, lightweight, benchmark, super-resolution | |
| Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration | IQPIR | CVPR 2026 | code | GAN, transformer, image, real-world, codebook, perceptual |
| Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration | RAR | CVPR 2026 | code | flow, diffusion, image, all-in-one, blind, restoration |
| EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions | EgoXtreme | CVPR 2026 | code | dataset, benchmark, real-world, 6dof, egocentric, motion-blur |
| DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution | DUO-VSR | CVPR 2026 | code | diffusion, DiT, GAN, one-step, video, super-resolution |
| OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging | OmniFM | CVPR 2026 | transformer, attention, medical, reconstruction, federated learning, frequency | |
| Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration | Face2Scene | CVPR 2026 | code | diffusion, SD-Turbo, LoRA, one-step, blind, restoration |
| Empowering Semantic-Sensitive Underwater Image Enhancement with VLM | - | AAAI 2026 | underwater, cross-attention, perceptual, LLaVA, image, enhancement | |
| UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution | UCAN | CVPR 2026 | code | attention, CNN, lightweight, large-kernel, linear-attention, super-resolution |
| Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis | UniCAC | CVPR 2026 | code | benchmark, CNN, transformer, blind, aberration correction, image |
| Compressed-Domain-Aware Online Video Super-Resolution | CDA-VSR | CVPR 2026 | code | CNN, video, compressed-domain, motion vectors, online, super-resolution |
| Disentangled Textual Priors for Diffusion-based Image Super-Resolution | DTPSR | CVPR 2026 | code | diffusion, cross-attention, frequency-aware, real-world, blind, super-resolution |
| Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset | Real-IISR | CVPR 2026 | code | autoregressive, codebook, infrared, real-world, super-resolution |
| CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video | CubeComposer | CVPR 2026 | code | diffusion, autoregressive, video, attention, 4K, 360 |
| All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network | CWP-Net | TIP | CNN, prompt, wavelet, blind, all-in-one, image | |
| FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution | FiDeSR | CVPR 2026 | code | diffusion, distillation, one-step, fidelity, image, super-resolution |
| Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration | DATPRL-IR | ICLR 2026 | code | transformer, prompt, distillation, image, all-in-one, restoration |
| Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design | DTIUIE | TIP | code | CNN, attention, underwater, perceptual, image |
| Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery | RepTRFD | CVPR 2026 | code | INR, tensor, reconstruction, inpainting, point cloud |
| Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement | UHDPromer | IJCV | code | transformer, attention, image, lightweight, restoration, 4K |
| ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration | ShiftLUT | CVPR 2026 | code | LUT, CNN, efficient, lightweight, image, restoration |
| AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution | AlignVAR | CVPR 2026 | autoregressive, attention, image, efficient, perceptual, super-resolution | |
| SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting | SR3R | CVPR 2026 | code | transformer, 3D, gaussian splatting, feed-forward, super-resolution |
| DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution | DACESR | TIP | code | Mamba, contrastive learning, real-world, image, super-resolution |
| Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction | ReMD | CVPR 2026 | code | diffusion, fluid, wavelet, multigrid, super-resolution |
| GSNR: Graph Smooth Null-Space Representation for Inverse Problems | GSNR | CVPR 2026 | graph laplacian, plug-and-play, diffusion, image, reconstruction, inverse problems | |
| Deep LoRA-Unfolding Networks for Image Restoration | LoRA | TIP | deep unfolding, LoRA, reconstruction, compressive sensing, image, efficient | |
| Vascular anatomy-aware self-supervised pre-training for X-ray angiogram analysis | XA-SSL | AAAI 2026 | code | transformer, masked image modeling, medical, pre-training, reconstruction |
| Eliminating VAE for Fast and High-Resolution Generative Detail Restoration | GenDR-Pix | ICLR 2026 | diffusion, distillation, one-step, real-world, 4K, super-resolution |