How ranker-adhipkumar/ai-image-restoration works
This is a CPU-friendly image-restoration application with Gradio and CLI entry points. Users can simulate damage for benchmarking or submit already-damaged images for blind diagnosis and restoration; the system then presents restoration results and quality assessments. The graph preserves the documented restoration modes, model fallbacks, sample-image support, and comparison visualizations. Some subsystem links come from the SOURCE INDEX or README because their implementation was not excerpted; those limits are reflected by omitting uncertain links.
Main entry points: app.py Gradio web app · __init__.py Restoration dispatcher · main.py Command-line app · blind_restorer.py Blind restoration
Components 17
User interfaces
- Gradio web app
app.py - Command-line app
main.py
Image workflows
- Degradation simulation
degradation.py - Blind restoration
restoration/blind_restorer.py
Restoration engines
- Restoration dispatcher
restoration/__init__.py - Denoising
restoration/denoiser.py - Deblurring
restoration/deblurrer.py - Inpainting
restoration/inpainter.py - Artifact removal
restoration/artifact_remover.py - NAFNet architecture
restoration/nafnet_arch.py
Quality and reporting
- Blind diagnostics
diagnostics.py - Reference metrics
metrics.py - Comparison visualizer
visualizer.py - Benchmark output generator
generate_demo_outputs.py
Image support
- Image I/O and helpers
utils.py - Sample downloader
sample_images/download_samples.py
Other components
- Image user
Connections 35
- Image user → Gradio web app: uploads image
README.md - Image user → Command-line app: provides image
README.md - Gradio web app → Degradation simulation: requests degradation
app.py - Gradio web app → Blind restoration: requests restoration
app.py - Gradio web app → Restoration dispatcher: requests restoration
app.py - Gradio web app → Blind diagnostics: requests diagnosis
app.py - Gradio web app → Reference metrics: requests metrics
app.py - Gradio web app → Comparison visualizer: renders comparisons
app.py - Gradio web app → Sample downloader: uses sample images
app.py - Command-line app → Degradation simulation: requests degradation
main.py - Command-line app → Blind restoration: requests restoration
main.py - Command-line app → Restoration dispatcher: requests restoration
main.py - Command-line app → Blind diagnostics: requests diagnosis
main.py - Command-line app → Reference metrics: requests metrics
main.py - Restoration dispatcher → Denoising: dispatches noise modes
restoration/__init__.py - Restoration dispatcher → Deblurring: dispatches blur modes
restoration/__init__.py - Restoration dispatcher → Inpainting: dispatches inpainting
restoration/__init__.py - Restoration dispatcher → Artifact removal: dispatches artifacts
restoration/__init__.py - Restoration dispatcher → Blind restoration: dispatches blind modes
restoration/__init__.py - Blind restoration → Blind diagnostics: diagnoses image
restoration/blind_restorer.py - Blind restoration → Denoising: applies denoising
restoration/blind_restorer.py - Blind restoration → Deblurring: applies deblurring
restoration/blind_restorer.py - Denoising → NAFNet architecture: uses model
restoration/denoiser.py - Deblurring → NAFNet architecture: uses model
restoration/deblurrer.py - Reference metrics → Blind diagnostics: uses diagnostics
metrics.py - Benchmark output generator → Degradation simulation: uses degradation
generate_demo_outputs.py - Benchmark output generator → Restoration dispatcher: uses restoration
generate_demo_outputs.py - Benchmark output generator → Reference metrics: computes metrics
generate_demo_outputs.py - Benchmark output generator → Comparison visualizer: creates comparisons
generate_demo_outputs.py - Gradio web app → Image I/O and helpers: uses image helpers
app.py - Command-line app → Image I/O and helpers: loads and resizes
main.py - Degradation simulation → Image I/O and helpers: uses image helpers
degradation.py - Blind diagnostics → Image I/O and helpers: uses image helpers
diagnostics.py - Reference metrics → Image I/O and helpers: uses image helpers
metrics.py - Comparison visualizer → Image I/O and helpers: uses image helpers
visualizer.py