neosr-project

CLP. Python

Submission-for-NTIRE-2025-SR-x4-. Python

MFG-HMoE. PyTorch codes for "Heterogeneous Mixture of Experts for Remote Sensing Image Super-Resolution", IEEE GRSL, 2025.

CATANet. CVPR2025 - CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution

ESC. [ICCV2025 Highlight] ESC: Emulating Self-attention with Convolution for Efficient Image Super-Resolution

CIKM2025-FR-KAN. FR-KAN official implementation

kat. [ICLR2025] Kolmogorov-Arnold Transformer

All-KAN. All-KAN: All Kolmogorov-Arnold Networks We Know

ASID. ASID

R3GAN. Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

ssort. Tool for automatically sorting python statements within a module

auto-walrus. Automatically use the awesome walrus operator

MoESR. Python

RCAN. PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

ntsc-rs. Free, open-source VHS effect. Standalone application + plugin (After Effects, Premiere, and OpenFX).

HeavyBall. Efficient optimizers

LAMNet. PyTorch Implementation of "Unifying Dimensions: A Linear Adaptive Mixer for Lightweight Image Super-Resolution"

Sebica. Official code for Sebica

CFSR. [IEEE TIP] Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach

FDL. [CVPR-2024] Official Pytorch implementation of "Misalignment-Robust Frequency Distribution Loss for Image Transformation"

MS-SWD. [ECCV 2024] Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures

FlexNet. Python

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

torchfix. TorchFix - a linter for PyTorch-using code with autofix support

mARWP. [TMLR 2024] Revisiting Random Weight Perturbation for Efficiently Improving Generalization

projected-distribution-loss. My implementation of Projected Distribution Loss (PDL)

DUnet. Python

HASN. Accepted by Visual Computer

PlainUSR. Series solutions for Faster SR (NTIRE/ACCV)

KRGN. PyTorch implementation of "Towards lightweight image super-resolution via re-parameterized kernel recalibration"

FIWHN. [TMM 2024] "Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network"

DCT. Python

LMLT. Code of "LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolution".

swin2-mose. Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing

vs_undistort. Vapoursynth function to remove video distortions, turbulance, wobble, warp, heat haze, or similar

vs_liif. AI resizing to arbitrary resolutions in Vapoursynth using LIIF. Upscaling and downscaling.

vs_align. Video Alignment and Synchronization functions for VapourSynth

vs_grain. Vapoursynth wrapper for fgrain and helper for overlaying external grain clips.

vs_temporalfix. VapourSynth function to add Temporal Coherence to AI Upscales

vs_iqa. Image Quality Assessment (IQA) function for Vapoursynth.

vs_colorfix. Color Fix, Color Transfer, or Color Match functions for Vapoursynth

EIMN. Efficient Information Modulation Network for Image Super-Resolution (ECAI-2023)

MoSR. Python

GRFormer. the code of GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution

IGConv. IGConv: Implicit Grid Convolution for Multi-Scale Image Super-Resolution

unpaired_hdr_tmo. Python

DegAE_DegradationAutoencoder. Codes for CVPR2023 paper "DegAE: A New Pretraining Paradigm for Low-level Vision"

VQD-SR. [ICCV'23] VQD-SR: Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

ReDSR. Official codes for 'Preserving Full Degradation Details for Blind Image Super-Resolution'

MAN. Multi-scale Attention Network for Single Image Super-Resolution (CVPRW 2024)

HMA. Python

HiT-SR. [ECCV 2024 - Oral] HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution

SPANPlus. Python

metaformer. MetaFormer Baselines for Vision (TPAMI 2024)

Patch-Loss-for-Super-Resolution. Python

RVSR. AIS 2024 Challenge, Real-Time 4K Super-Resolution of Compressed AVIF Images (Runner-Up Award in Track: Fidelity PSNR), Team XJTU-AIR

dysample. (ICCV'23) Learning to Upsample by Learning to Sample

F-SAM. [CVPR 2024] Friendly Sharpness-Aware Minimization

sam. SAM: Sharpness-Aware Minimization (PyTorch)

universal_sam. Python

IQA-PyTorch. 🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

schedule_free. Schedule-Free Optimization in PyTorch

ECO. [AAAI2024] Official Repository for Noise-free Optimization in Early Training Steps for Image Super-Resolution

win. Python

seemoredetails. [ICML 2024] See More Details: Efficient Image Super-Resolution by Experts Mining

MC-optimizer. optimizer for convolutional neural networks

Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution. Python

models. All my self trained & released AI upscaling models. After gathering and applying over 600 different upscaling models, I learned how to train my own models, and these are the results.

WGSR. [CVPR 2024] Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

DISTS. IQA: Deep Image Structure and Texture Similarity Metric

gradient-variance-loss. Code of the ICASSP 2022 paper "Gradient Variance Loss for Structure Enhanced Super-Resolution"

mssim.pytorch. A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.

MSDAN. Lightweight multi-scale distillation attention network for image super-resolution

AGDN. Attention Guidance Distillation Network for Efficient Image Super-Resolution

DRCT. Accepted by New Trends in Image Restoration and Enhancement workshop (NTIRE), in conjunction with CVPR 2024.

PLKSR. [IEEE Access] Partial Large Kernel CNNs for Efficient Super-Resolution

SAFMN. [ICCV 2023] Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution; runner-up method for the model complexity track in NTIRE2023 Efficient SR challenge

RGT. [ICLR'24] Recursive Generalization Transformer for Image Super-Resolution

PCL-SISR. [IEEE TNNLS] A Practical Contrastive Learning Framework for Single Image Super-Resolution

luminal. Inference at the speed of light.

A-DISTS. Locally Adaptive DISTS

AsConvSR-TorchLighting. Python

Adaptive-Token-Dictionary. [CVPR 2024 & TPAMI] Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary, ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration

APISR. APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

ruff. An extremely fast Python linter and code formatter, written in Rust.

ruff-pre-commit. A pre-commit hook for Ruff.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

traiNNer. traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.

upscale-resources. How to start training AI models (restoration, upscaling)

focal-frequency-loss. [ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

LDL. Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

Adan. Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

A2-FPN. The semantic segmentation of remote sensing images

CRAFT-SR. [ICCV2023] Implementation of "Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution"

EDAT. Official implementation of "Efficient Dual Attention Transformer for Image Super-Resolution"

DWT. Official implementation of "Image Super-Resolution Using Dilated Window Transformer", IEEE Access 2023.

ailab. Python

DAT. [ICCV'23] Dual Aggregation Transformer for Image Super-Resolution

SRFormer. Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

Omni-SR. [CVPR2023] Implementation of ''Omni Aggregation Networks for Lightweight Image Super-Resolution".

HAT. CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer TPAMI - HAT: Hybrid Attention Transformer for Image Restoration

BasicSR. Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

DCTLSA. Densely Connected Transformer with Linear Self-Attention for Lightweight Image Super-Resolution

NLSAN. Python

SPAN. Swift Parameter-free Attention Network for Efficient Super-Resolution

DiffIR. This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

cutblur. Rethinking Data Augmentation for Image Super-resolution (CVPR 2020)

DITN. Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution

Awesome-diffusion-model-for-image-processing. one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

framework-reproducibility. Providing reproducibility in deep learning frameworks

AnimeSR. Codes for "AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos"

cudarc. Safe rust wrapper around CUDA toolkit

dfdx. Deep learning in Rust, with shape checked tensors and neural networks

llama-dfdx. LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!

MDT. Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

LUD-VAE. Official code for "Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach"

ESRGAN. A modified version of the original ESRGAN test.py script with added features

traiNNer-redux. (Fork of BasicSR) Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

open-model-database. An open and free database for AI models

SCUNet. Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)

KUNet. IJCAI2022

chaiNNer. A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.

ghost. A new one shot face swap approach for image and video domains

MM-RealSR. Codes for "Metric Learning based Interactive Modulation for Real-World Super-Resolution"

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

SwinIR. SwinIR: Image Restoration Using Swin Transformer (official repository)

MODNet. A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

automatic-recolorization. Uses ML colorization methods to restore image color (RGB -> IR (Gray+extra data) -> RGB)

FBCNN. Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

style-transfer-pytorch. Neural style transfer in PyTorch.

Deep-HdrReconstruction. Official PyTorch implementation of "Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss" (SIGGRAPH 2020)

GFPGAN. GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

resdet. Detect source resolution of upscaled images and videos

Zero-DCE_extension. Python

Practical-RIFE. More practical frame interpolation approach.

ECCV2022-RIFE. ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

hdr-expandnet. Training and inference code for ExpandNet

DeblurGANv2. [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

DPIR. Plug-and-Play Image Restoration with Deep Denoiser Prior (IEEE TPAMI 2021) (PyTorch)