# xpixelgroup/basicsr

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/xpixelgroup-basicsr).**

8,297 stars · 1,409 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/XPixelGroup/BasicSR
- Homepage: https://basicsr.readthedocs.io/en/latest/
- awesome-repositories: https://awesome-repositories.com/repository/xpixelgroup-basicsr.md

## Topics

`basicsr` `basicvsr` `dfdnet` `ecbsr` `edsr` `edvr` `esrgan` `pytorch` `rcan` `restoration` `srgan` `srresnet` `stylegan2` `super-resolution` `swinir`

## Description

BasicSR is a PyTorch-based image restoration toolbox and framework designed for training and deploying deep learning models to upscale, denoise, and deblur images and videos. It serves as a comprehensive system for image super-resolution and video quality restoration, providing the necessary infrastructure to recover fine visual details and increase pixel density.

The project distinguishes itself through specialized toolkits for facial image enhancement and high-fidelity face synthesis, as well as a dedicated video quality restoration suite that utilizes deformable convolutions and generative adversarial networks to maintain temporal consistency. It also includes an image quality evaluation suite with metrics such as PSNR, SSIM, LPIPS, and FID to quantify the fidelity of restored visual media.

The framework covers a broad range of capability areas, including data engineering pipelines for synthesizing image degradations and optimizing datasets via memory-mapped storage. It provides extensive support for model management, distributed training synchronization, and the implementation of various neural architectures, such as transformers and residual networks.

The system is designed for extensibility through configuration-driven model instantiation and a registry-based module mapping system.

## Tags

### Graphics & Multimedia

- [Image and Video Restoration Suites](https://awesome-repositories.com/f/graphics-multimedia/image-and-video-restoration-suites.md) — Provides a comprehensive framework for improving video resolution and removing artifacts while maintaining temporal consistency. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.edvr_model.html))
- [Dynamic Image Upsampling](https://awesome-repositories.com/f/graphics-multimedia/3d-point-cloud-filtering/resolution-upsampling/dynamic-image-upsampling.md) — Increases the spatial dimensions of images or feature maps by a scale factor to improve resolution. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.arch_util.html))
- [Image Noise Reduction](https://awesome-repositories.com/f/graphics-multimedia/image-noise-reduction.md) — Implements algorithms for removing grain and electronic noise from digital images while preserving structural details. ([source](https://cdn.jsdelivr.net/gh/xpixelgroup/basicsr@master/README.md))
- [Image Noise Simulations](https://awesome-repositories.com/f/graphics-multimedia/image-noise-simulations.md) — Simulates sensor degradation and image artifacts by applying Gaussian noise, Poisson noise, and JPEG compression. ([source](https://basicsr.readthedocs.io/en/latest/api/api_basicsr.html))
- [Image Similarity Estimation](https://awesome-repositories.com/f/graphics-multimedia/image-similarity-estimation.md) — Quantifies restoration quality by calculating the resemblance between images using PSNR and SSIM. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.metrics.test_metrics.test_psnr_ssim.html))
- [Face Restoration](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/image-processing/face-restoration.md) — Recovers fine details and sharpens low-resolution facial images using deep face dictionary networks. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.dfdnet_arch.html))
- [Facial Restoration](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/media-processing-workflows/generative-visual-engines/generative-image-enhancements/facial-restoration.md) — Implements generative techniques for reconstructing high-fidelity facial details and removing artifacts from face images.
- [Restoration Quality Metrics](https://awesome-repositories.com/f/graphics-multimedia/restoration-quality-metrics.md) — Calculates objective quality metrics like PSNR, SSIM, NIQE, and FID to evaluate restoration fidelity. ([source](https://basicsr.readthedocs.io/en/latest/api/api_basicsr.html))
- [Video Restoration Tools](https://awesome-repositories.com/f/graphics-multimedia/video-restoration-tools.md) — Implements tools for removing artifacts and improving resolution in video sequences using deformable convolutions and GANs.
- [Recurrent Restoration](https://awesome-repositories.com/f/graphics-multimedia/video-restoration-tools/recurrent-restoration.md) — Uses recurrent architectures to improve video resolution while maintaining temporal consistency between frames. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.video_recurrent_gan_model.html))
- [Image Sharpening](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/rendering/post-processing-effects/image-sharpening.md) — Enhances image edges by blending blurred versions with original images to increase visual sharpness. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.img_process_util.html))
- [Image Dimension Standardizations](https://awesome-repositories.com/f/graphics-multimedia/image-dimension-standardizations.md) — Normalizes image array channel orders to ensure a consistent height-width-channel format for ML models. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.metrics.metric_util.html))
- [Importance-Based Pooling](https://awesome-repositories.com/f/graphics-multimedia/image-downsampling/importance-based-pooling.md) — Implements structure-preserving downsampling of feature maps to maintain critical local details during restoration. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.hifacegan_util.html))
- [Sliding Window Patching](https://awesome-repositories.com/f/graphics-multimedia/image-editing-processing/image-editors/image-cropping-tools/sliding-window-patching.md) — Slices large images into smaller patches using a sliding window to optimize GPU memory usage. ([source](https://basicsr.readthedocs.io/en/latest/api/scripts.data_preparation.extract_subimages.html))
- [Bicubic Interpolation](https://awesome-repositories.com/f/graphics-multimedia/image-editing-processing/image-processing/dimension-resizing/bicubic-interpolation.md) — Performs high-quality image resizing using bicubic interpolation with optional anti-aliasing. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.matlab_functions.html))
- [FIR Filter Resizing](https://awesome-repositories.com/f/graphics-multimedia/image-editing-processing/image-processing/dimension-resizing/fir-filter-resizing.md) — Resizes images using a 2D FIR filter for precise kernel application and controlled padding. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.ops.upfirdn2d.__init__.html))
- [Training Format Optimizers](https://awesome-repositories.com/f/graphics-multimedia/image-memory-optimizations/training-format-optimizers.md) — Provides utilities to transform raw images into binary-optimized formats to accelerate training throughput. ([source](https://basicsr.readthedocs.io/en/latest/api/api_scripts.html))
- [Degradation Simulation Pipelines](https://awesome-repositories.com/f/graphics-multimedia/image-noise-simulations/degradation-simulation-pipelines.md) — Generates synthetic training data by simulating real-world quality loss via Gaussian noise, blur, and JPEG artifacts.
- [Pixel Value Normalization](https://awesome-repositories.com/f/graphics-multimedia/image-to-tensor-conversions/pixel-value-normalization.md) — Adjusts RGB channel values using mean and standard deviation for consistent distribution across batches. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.ridnet_arch.html))
- [JPEG Compression Simulation](https://awesome-repositories.com/f/graphics-multimedia/jpeg-compression-simulation.md) — Simulates lossy JPEG encoding artifacts to generate degraded training data for restoration models. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.degradations.html))
- [JPEG Decompression Simulation](https://awesome-repositories.com/f/graphics-multimedia/jpeg-decompression-simulation.md) — Provides tools to simulate the reconstruction process of compressed JPEG images for research into restoration artifacts. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.diffjpeg.html))
- [Neural Artifact Removal](https://awesome-repositories.com/f/graphics-multimedia/neural-artifact-removal.md) — Uses neural networks to eliminate JPEG compression artifacts and restore visual fidelity. ([source](https://basicsr.readthedocs.io/en/latest/))
- [Perceptual Similarity Scoring](https://awesome-repositories.com/f/graphics-multimedia/perceptual-similarity-scoring.md) — Quantifies human perception similarity between two images using a deep network. ([source](https://basicsr.readthedocs.io/en/latest/api/scripts.metrics.calculate_lpips.html))
- [Pixel-Level Fidelity Metrics](https://awesome-repositories.com/f/graphics-multimedia/pixel-level-fidelity-metrics.md) — Calculates peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) to quantify image differences. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.metrics.__init__.html))
- [Restoration Validation](https://awesome-repositories.com/f/graphics-multimedia/video-restoration-tools/restoration-validation.md) — Executes full processing pipelines to verify the visual quality and structural integrity of the restoration workflow. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.test.html))
- [Video Upscaling Pipelines](https://awesome-repositories.com/f/graphics-multimedia/video-upscaling-pipelines.md) — Implements video upscaling pipelines that support 4x resolution increase and alignment modules. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.basicvsr_arch.html))

### Artificial Intelligence & ML

- [Adversarial Loss Functions](https://awesome-repositories.com/f/artificial-intelligence-ml/adversarial-loss-functions.md) — Implements adversarial loss functions including LSGAN and WGAN to improve image realism. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.losses.gan_loss.html))
- [Detail Reconstruction](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-portrait-composition/facial-feature-refinement/detail-reconstruction.md) — Implements generative processes for restoring high-fidelity textures and fine details specifically in facial images. ([source](https://cdn.jsdelivr.net/gh/xpixelgroup/basicsr@master/README.md))
- [Restoration Benchmarks](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-benchmarks/restoration-benchmarks.md) — Computes standard restoration benchmarks including PSNR, SSIM, LPIPS, NIQE, and FID. ([source](https://basicsr.readthedocs.io/en/latest/api/api_scripts.html))
- [Image Blur Removal](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks/image-restorers/image-blur-removal.md) — Corrects motion or focus blur to sharpen edges and restore visual structures in images. ([source](https://cdn.jsdelivr.net/gh/xpixelgroup/basicsr@master/README.md))
- [Degradation Modeling](https://awesome-repositories.com/f/artificial-intelligence-ml/degradation-modeling.md) — Creates paired training datasets by simulating real-world quality loss via configurable degradation parameters. ([source](https://basicsr.readthedocs.io/en/latest/))
- [Resolution Upscalers](https://awesome-repositories.com/f/artificial-intelligence-ml/example-based-image-generation/resolution-upscalers.md) — Increases image resolution by synthesizing high-frequency details using neural network architectures. ([source](https://cdn.jsdelivr.net/gh/xpixelgroup/basicsr@master/README.md))
- [Video](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-alignment/video.md) — Aligns deep features across video frames using modulated convolutions to ensure temporal consistency. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.arch_util.html))
- [GAN Regularization Techniques](https://awesome-repositories.com/f/artificial-intelligence-ml/gan-regularization-techniques.md) — Computes gradient penalties and R1 regularization loss to stabilize generative adversarial networks. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.losses.__init__.html))
- [Image Restoration Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/image-restoration-models/image-restoration-model-training.md) — Provides an optimized training pipeline with customizable loss functions and learning rate schedulers specifically for image restoration. ([source](https://basicsr.readthedocs.io/en/latest/api/api_basicsr.html))
- [Image Super Resolution Models](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models.md) — Implements deep learning architectures designed to increase image resolution and reconstruct fine visual details.
- [Blind Super-Resolution](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/blind-super-resolution.md) — Implements upscaling techniques that use synthetic degradation data to handle unknown real-world blur and noise. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.realesrnet_model.html))
- [Perceptual Loss](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/loss-functions/perceptual-loss.md) — Calculates perceptual loss by extracting network features to compare high-level visual patterns. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.losses.basic_loss.html))
- [Pixel-Wise Reconstruction Losses](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/loss-functions/perceptual-loss/content-loss-calculators/focal-loss-calculators/detection-loss-calculators/smooth-l1-loss-calculators/regression-loss-functions/pixel-wise-reconstruction-losses.md) — Computes L1, MSE, and Charbonnier distances between tensors to ensure reconstruction accuracy. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.losses.basic_loss.html))
- [Deformable Convolutions](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/convolution-layers/deformable-convolutions.md) — Uses learnable offsets in convolutional layers to adaptively sample features for motion compensation in videos.
- [Image Convolutions](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/machine-learning-concepts/network-architectures-and-layers/image-convolutions.md) — Performs fundamental two-dimensional convolution operations on image tensors to extract spatial features. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.img_process_util.html))
- [Synthetic Data Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/synthetic-data-pipelines.md) — Provides an automated pipeline for synthesizing image degradations, including Gaussian noise and JPEG artifacts, for training.
- [Gradient Penalties](https://awesome-repositories.com/f/artificial-intelligence-ml/training-stability-techniques/gradient-penalties.md) — Stabilizes discriminator training using gradient norm penalties and R1 regularization. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.losses.gan_loss.html))
- [Feature Warping Modules](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-field-estimation/optical-flow-computation/feature-warping-modules.md) — Transforms images or feature maps based on optical flow fields to align temporal frames. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.arch_util.html))
- [Attention-Based Upscaling](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks/image-restorers/attention-based-upscaling.md) — Implements resolution enhancement using channel and spatial attention networks such as RCAN. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.rcan_arch.html))
- [Deep Learning Training Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-training-pipelines.md) — Ships end-to-end workflows for data ingestion using LMDB and synthesis of image degradations for model training.
- [Dense Block Upscaling](https://awesome-repositories.com/f/artificial-intelligence-ml/example-based-image-generation/resolution-upscalers/dense-block-upscaling.md) — Implements high-fidelity resolution enhancement using residual-in-residual dense block architectures. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.rrdbnet_arch.html))
- [Generative Image Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-image-models.md) — Provides frameworks for training and deploying generative image models that support noise mixing for high-fidelity synthesis. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.stylegan2_model.html))
- [Distributed Gradient Synchronization](https://awesome-repositories.com/f/artificial-intelligence-ml/gradient-computation/distributed-gradient-synchronization.md) — Coordinates and averages loss values across multiple GPUs to ensure consistent model updates during parallel training.
- [Tensor Patch Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/image-convolution-operations/image-patch-embedders/tensor-patch-extraction.md) — Extracts random paired patches or uses modulo cropping to maintain consistent dimensions for testing. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.transforms.html))
- [Adversarial Upscaling Training](https://awesome-repositories.com/f/artificial-intelligence-ml/image-restoration-models/image-restoration-model-training/adversarial-upscaling-training.md) — Provides processes for training GANs by synthesizing low-quality pairs to optimize restoration performance. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.realesrgan_model.html))
- [Dataset Preparation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/dataset-preparation.md) — Implements processes for creating training pairs by applying degradations to high-resolution ground-truth images. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.realesrgan_dataset.html))
- [Facial Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/high-resolution-synthesis/facial-synthesis.md) — Generates high-fidelity synthetic faces using deep learning encoders and generators. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.hifacegan_arch.html))
- [Real-Time Super-Resolution](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/real-time-super-resolution.md) — Provides optimized architectures designed for high-speed image resolution increase on resource-constrained devices. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.ecbsr_arch.html))
- [Propagation-Based Upsampling](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/video-super-resolution-suites/propagation-based-upsampling.md) — Increases video resolution using propagation and alignment techniques to ensure temporal quality. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.basicvsrpp_arch.html))
- [Task-Oriented Flow Enhancement](https://awesome-repositories.com/f/artificial-intelligence-ml/image-super-resolution-models/video-super-resolution-suites/task-oriented-flow-enhancement.md) — Processes low-resolution video frames into high-resolution output using task-oriented flow. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.tof_arch.html))
- [Learning Rate Decay Schedules](https://awesome-repositories.com/f/artificial-intelligence-ml/learning-rate-decay-schedules.md) — Adjusts learning rates over time using cosine annealing and multi-step decay schedules. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.lr_scheduler.html))
- [Learning Rate Schedulers](https://awesome-repositories.com/f/artificial-intelligence-ml/learning-rate-schedulers.md) — Schedules learning rate updates based on training iterations and warmup phases. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.base_model.html))
- [Swin Transformer Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/transformer-architectures/swin-transformer-implementations.md) — Implements transformer-based architectural stages with configurable attention heads for image restoration. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.swinir_arch.html))
- [Model Complexity Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/model-complexity-analysis.md) — Analyzes and compares the computational resource requirements and efficiency of various restoration architectures. ([source](https://basicsr.readthedocs.io/en/latest/api/api_scripts.html))
- [Spatially-Adaptive Normalization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/spatial-control-networks/spatially-adaptive-normalization.md) — Modulates activations based on semantic segmentation maps to inject spatial layout information. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.hifacegan_util.html))
- [Model Weight Management](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-management.md) — Imports model weights from file paths with optional strictness checks for initialization. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.base_model.html))
- [Weight Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-management/weight-transformations/weight-persistence.md) — Saves network weights and training states to disk to allow for model deployment or training resumption. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.base_model.html))
- [Training Checkpointing](https://awesome-repositories.com/f/artificial-intelligence-ml/training-checkpointing.md) — Saves network weights and training progress to disk as checkpoints to ensure fault tolerance and resume capabilities. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.models.sr_model.html))
- [Training Data Prefetchers](https://awesome-repositories.com/f/artificial-intelligence-ml/training-data-prefetchers.md) — Implements background queue loading of training samples to maximize GPU throughput and prevent starvation.
- [Image Augmentations](https://awesome-repositories.com/f/artificial-intelligence-ml/training-data-transformations/image-augmentations.md) — Applies random horizontal flips and rotations to images and optical flows to improve model generalization. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.transforms.html))
- [Training Workflow Coordination](https://awesome-repositories.com/f/artificial-intelligence-ml/training-workflow-coordination.md) — Coordinates data loading, event logging, and state restoration throughout the restoration training process. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.train.html))
- [Optical Flow Computation](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-field-estimation/optical-flow-computation.md) — Calculates pixel motion between video frames to align features across a sequence. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.basicvsrpp_arch.html))

### Data & Databases

- [Training Data Pipelines](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-processing/ml-data-pipelines/training-data-pipelines.md) — Initializes data loading pipelines from configuration files to prepare training and validation image pairs. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.__init__.html))
- [Image Path Pairers](https://awesome-repositories.com/f/data-databases/image-dataset-imports/siamese-pair-builders/image-path-pairers.md) — Matches input and ground-truth image paths to construct aligned paired datasets for restoration training. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.data.data_util.html))
- [LMDB Dataset Converters](https://awesome-repositories.com/f/data-databases/lmdb-dataset-converters.md) — Packages image datasets into LMDB files to accelerate data loading and minimize disk I/O overhead.
- [LMDB Image Packagers](https://awesome-repositories.com/f/data-databases/lmdb-image-packagers.md) — Provides systems for bundling image files and metadata into LMDB databases with optional compression. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.lmdb_util.html))

### Testing & Quality Assurance

- [Image Restoration Metrics](https://awesome-repositories.com/f/testing-quality-assurance/performance-testing-analysis/performance-diagnostics/performance-measurement/image-restoration-metrics.md) — Evaluates restored images using quantitative fidelity metrics such as PSNR and FID. ([source](https://basicsr.readthedocs.io/en/latest/py-modindex.html))

### Part of an Awesome List

- [No-Reference Quality Metrics](https://awesome-repositories.com/f/awesome-lists/ai/image-quality-assessment/no-reference-quality-metrics.md) — Evaluates image naturalness using the NIQE no-reference quality metric. ([source](https://basicsr.readthedocs.io/en/latest/api/scripts.metrics.calculate_niqe.html))
- [Motion Estimation Networks](https://awesome-repositories.com/f/awesome-lists/ai/video-restoration/motion-estimation-networks.md) — Implements the SpyNet architecture specifically for motion estimation and temporal alignment in video restoration. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.archs.spynet_arch.html))

### DevOps & Infrastructure

- [Configuration File Loading](https://awesome-repositories.com/f/devops-infrastructure/configuration-management/file-based-configuration/configuration-file-loading.md) — Parses YAML configuration files into dictionaries to initialize model hyperparameters and runtime behavior. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.options.html))

### Programming Languages & Runtimes

- [Configuration-Driven Instantiations](https://awesome-repositories.com/f/programming-languages-runtimes/class-instantiation/configuration-driven-instantiations.md) — Provides automatic model instantiation by parsing YAML configurations and dictionaries into network architectures.

### Scientific & Mathematical Computing

- [Fréchet Inception Distances](https://awesome-repositories.com/f/scientific-mathematical-computing/numerical-mathematical-foundations/mathematical-libraries-and-utilities/core-mathematical-concepts/distance-metrics/coordinate-distance-transformations/euclidean-distance-calculators/perceptual-distance-calculators/frechet-inception-distances.md) — Measures similarity between real and generated image sets using feature means and covariances. ([source](https://basicsr.readthedocs.io/en/latest/api/scripts.metrics.calculate_fid_folder.html))

### Software Engineering & Architecture

- [Component Registries](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/dependency-injection/component-registries.md) — Implements a registry system that maps unique names to objects for pluggable integration of third-party components.
- [Module-Based Registries](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/dependency-injection/module-based-registries.md) — Integrates third-party modules using a registry-based system to extend the framework without modifying core code. ([source](https://basicsr.readthedocs.io/en/latest/api/basicsr.utils.registry.html))