How algolzw/daclip-uir works
DA-CLIP is a controlled vision-language image-restoration system, with both the original DA-CLIP-SDE configuration and the later wild-IR variant. The user workflow takes a degraded image, extracts image and degradation context with DA-CLIP, and conditions an SDE-based restoration model to produce an output image. The repository also includes CLIP training/modeling, restoration training, and degradation/data utilities. Edges reflect the README and shown call sites; unsampled subsystems are included where documented, without assuming their internal wiring.
Main entry points: denoising_model.py Denoising Model · inference.py Wild-IR Inference · wild-ir/app.py Wild-IR Demo · daclip-sde/app.py DA-CLIP-SDE Demo
Components 24
Restoration Inference
- Wild-IR Demo
universal-image-restoration/config/wild-ir/app.py - DA-CLIP-SDE Demo
universal-image-restoration/config/daclip-sde/app.py - Wild-IR Inference
universal-image-restoration/config/wild-ir/inference.py
Vision Language Model
- CLIP Factory
universal-image-restoration/open_clip/factory.py - CLIP Encoders
universal-image-restoration/open_clip/model.py - Transformer Layers
universal-image-restoration/open_clip/transformer.py - Pretrained Weights
universal-image-restoration/open_clip/pretrained.py - CoCa Model
da-clip/src/open_clip/coca_model.py - Zero-Shot Metadata
da-clip/src/open_clip/zero_shot_metadata.py
Restoration Models
- Denoising Model
universal-image-restoration/config/wild-ir/models/denoising_model.py - Restoration Network
universal-image-restoration/config/wild-ir/models/networks.py - SDE Sampling
universal-image-restoration/utils/sde_utils.py - Matching Loss
universal-image-restoration/config/wild-ir/models/modules/loss.py - Optimizer Setup
universal-image-restoration/config/wild-ir/models/optimizer.py - Learning-Rate Schedule
universal-image-restoration/config/wild-ir/models/lr_scheduler.py - Restoration Options
universal-image-restoration/config/wild-ir/options.py
Training and Data
- Paired Image Datasets
universal-image-restoration/data/LQGT_dataset.py - Degradation Utilities
universal-image-restoration/data/deg_util.py - CLIP Training Data
da-clip/src/training/data.py - CLIP Training Loop
da-clip/src/training/train.py - CLIP Training Entry
da-clip/src/training/main.py - Distributed Training
da-clip/src/training/distributed.py - Training Parameters
da-clip/src/training/params.py
Other components
- Image User
Connections 27
- Image User → Wild-IR Demo: submits image
universal-image-restoration/config/wild-ir/app.py - Wild-IR Demo → CLIP Factory: loads DA-CLIP
universal-image-restoration/config/wild-ir/app.py - Wild-IR Demo → CLIP Encoders: encodes image
universal-image-restoration/config/wild-ir/app.py - Wild-IR Demo → SDE Sampling: adds noise
universal-image-restoration/config/wild-ir/app.py - Wild-IR Demo → Denoising Model: feeds and tests
universal-image-restoration/config/wild-ir/app.py - DA-CLIP-SDE Demo → CLIP Factory: loads DA-CLIP
universal-image-restoration/config/daclip-sde/app.py - DA-CLIP-SDE Demo → CLIP Encoders: encodes image
universal-image-restoration/config/daclip-sde/app.py - DA-CLIP-SDE Demo → SDE Sampling: adds noise
universal-image-restoration/config/daclip-sde/app.py - DA-CLIP-SDE Demo → Denoising Model: feeds and tests
universal-image-restoration/config/daclip-sde/app.py - Wild-IR Inference → CLIP Factory: loads DA-CLIP
universal-image-restoration/config/wild-ir/inference.py - Wild-IR Inference → CLIP Encoders: encodes image
universal-image-restoration/config/wild-ir/inference.py - Wild-IR Inference → SDE Sampling: adds noise
universal-image-restoration/config/wild-ir/inference.py - Wild-IR Inference → Denoising Model: feeds and tests
universal-image-restoration/config/wild-ir/inference.py - Wild-IR Inference → Paired Image Datasets: loads test data
universal-image-restoration/config/wild-ir/inference.py - CLIP Encoders → Transformer Layers: uses layers
universal-image-restoration/open_clip/model.py - Denoising Model → Restoration Network: builds network
universal-image-restoration/config/wild-ir/models/denoising_model.py - Denoising Model → Matching Loss: uses loss
universal-image-restoration/config/wild-ir/models/denoising_model.py - Denoising Model → Optimizer Setup: sets optimizer
universal-image-restoration/config/wild-ir/models/denoising_model.py - Denoising Model → Learning-Rate Schedule: sets schedule
universal-image-restoration/config/wild-ir/models/denoising_model.py - Paired Image Datasets → Degradation Utilities: uses utilities
universal-image-restoration/data/LQGT_dataset.py - CLIP Training Entry → CLIP Training Data: imports data
da-clip/src/training/main.py - CLIP Training Entry → CLIP Training Loop: imports training loop
da-clip/src/training/main.py - CLIP Training Entry → Distributed Training: imports distributed setup
da-clip/src/training/main.py - CLIP Training Entry → Training Parameters: imports parameters
da-clip/src/training/main.py - Wild-IR Demo → Denoising Model: configures model
universal-image-restoration/config/wild-ir/app.py - DA-CLIP-SDE Demo → Denoising Model: configures model
universal-image-restoration/config/daclip-sde/app.py - Wild-IR Inference → Restoration Options: parses options
universal-image-restoration/config/wild-ir/inference.py