Initial release

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+---
+library_name: pytorch
+pipeline_tag: image-to-image
+base_model: facebook/dinov3-vitl16-pretrain-lvd1689m
+tags:
+  - image-restoration
+  - all-in-one-restoration
+  - continual-learning
+  - neurips-2026
+---
+# DUDA pretrained release
+
+Pretrained assets for **Discovering Unseen Degradations to Adapt Semi-Supervised Image Restoration** (NeurIPS 2026).
+
+- Project: https://bo-oseng.github.io/DUDA/
+- Code: https://github.com/bo-oseng/DUDA
+- Dataset: https://huggingface.co/datasets/ses7720/DUDA-WRES
+
+## Files
+
+`duda-pretrained.tar.gz` contains the paper assets (about 193 MiB compressed):
+
+| Asset | Purpose |
+|---|---|
+| `checkpoints/stage0_latest.pth` | Supervised restoration initialization, epoch 500 |
+| `checkpoints/semi_supervised_epoch10.pth` | Adapted student/teacher and descriptor, epoch 10, step 14,470 |
+| `cgcd/` | PCA, scaler, class mapping and stage Gaussian parameters |
+| `dino_adapter/` | Learned DINOv3 BOFT adapter, permutation buffers, base-layer biases and classification head |
+| `features/wres_with_clear/dinov3-vitl16-sl/class_order.txt` | Degradation class ordering |
+| `manifest.json` | Per-file SHA-256 checksums |
+
+The Docker image below includes the runtime and implementation, so a GitHub
+checkout is optional for Docker users.
+
+DINOv3 base weights are obtained from the official gated model repository separately.
+
+## Download and run
+
+```bash
+hf download ses7720/DUDA --include "duda-pretrained.tar.gz*" README.md SHA256SUMS release.json --local-dir downloads/duda-models
+cd downloads/duda-models
+sha256sum -c SHA256SUMS
+tar -xzf duda-pretrained.tar.gz
+```
+
+From a [DUDA source checkout](https://github.com/bo-oseng/DUDA), follow its `README.md` to build the Conda environment or Docker image. Obtain
+DINOv3 using the access/download instructions in `README.md`, then link the
+extracted release assets:
+
+```bash
+python scripts/link_assets.py \
+  --features /path/to/duda-pretrained/features \
+  --dino-adapter /path/to/duda-pretrained/dino_adapter \
+  --cgcd /path/to/duda-pretrained/cgcd \
+  --stage0 /path/to/duda-pretrained/checkpoints/stage0_latest.pth \
+  --adapted /path/to/duda-pretrained/checkpoints/semi_supervised_epoch10.pth
+CUDA_VISIBLE_DEVICES=0 python restoration/infer.py \
+  --input /path/to/image.jpg --output outputs/restored.png
+```
+
+The default restoration checkpoint uses the adapted teacher. Add `--stage 0`
+for supervised initialization. The training patches can be generated from the
+original training images with the provided code, or downloaded directly as a
+precomputed archive. See the dataset card for both commands.
+
+## Continual 6+1+2 and 6+1+1+1 streams
+
+The optional `continual/duda-continual-weights.tar.gz` contains five regular-stream restoration checkpoints (two stages for 6+1+2 and three for 6+1+1+1), plus each stream's PCA, scaler, class mappings, and stage-specific CGCD means/covariances. The stage-aware source and Bash scripts are maintained in the [DUDA GitHub repository](https://github.com/bo-oseng/DUDA) and documented in `CONTINUAL.md`. The Docker image includes these scripts.
+
+```bash
+hf download ses7720/DUDA --include 'continual/duda-continual-weights.tar.gz' --local-dir downloads/duda-models
+cd /path/to/DUDA
+tar -xzf /path/to/downloads/duda-models/continual/duda-continual-weights.tar.gz --strip-components=1
+STAGE=2 bash bash/test_6p1p2.sh
+STAGE=3 bash bash/test_6p1p1p1.sh
+```
+
+## Downloadable Docker image
+
+The optional `docker/duda-neurips2026.tar.zst` file (7.00 GB compressed) contains the tested Docker
+image, including the runtime and project code. It is separate from the model
+bundle. Model weights, DINOv3 base weights and datasets are obtained separately.
+
+Download and load the image:
+
+```bash
+hf download ses7720/DUDA --include "docker/*" --local-dir downloads/duda-docker
+(cd downloads/duda-docker/docker && sha256sum -c SHA256SUMS)
+zstd -dc downloads/duda-docker/docker/duda-neurips2026.tar.zst | docker load
+```
+
+The loaded tag is `duda:neurips2026`. This is an image archive for `docker load`;
+it is not a Docker registry endpoint.
+
+To run one image, first extract `duda-pretrained.tar.gz` in your working directory.
+Request access to the [official DINOv3 model](https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m),
+then download its base weights:
+
+```bash
+hf auth login
+hf download facebook/dinov3-vitl16-pretrain-lvd1689m \
+  --revision ea8dc2863c51be0a264bab82070e3e8836b02d51 \
+  --include config.json model.safetensors preprocessor_config.json LICENSE.md README.md \
+  --local-dir dinov3-vitl16
+```
+
+Set your input image path and run the container. Change the host GPU selection
+as needed; the process inside the container uses the single exposed GPU.
+
+```bash
+export DUDA_INPUT=/absolute/path/to/input.jpg
+mkdir -p outputs
+docker run --rm --gpus '"device=0"' --shm-size=2g \
+  -v "$PWD/dinov3-vitl16:/app/assets/dino_base:ro" \
+  -v "$PWD/duda-pretrained/dino_adapter:/app/assets/dino_adapter:ro" \
+  -v "$PWD/duda-pretrained/cgcd:/app/assets/cgcd:ro" \
+  -v "$PWD/duda-pretrained/features:/app/assets/features:ro" \
+  -v "$PWD/duda-pretrained/checkpoints:/app/assets/checkpoints:ro" \
+  -v "$DUDA_INPUT:/inputs/input.jpg:ro" \
+  -v "$PWD/outputs:/app/outputs" \
+  duda:neurips2026 python restoration/infer.py \
+    --input /inputs/input.jpg --output outputs/restored.png
+```
+
+The image pins Pillow 11.3.0, whose libjpeg-turbo JPEG decoding matches the
+paper runs.
+
+The image can also run `scripts/prepare_datasets.py` for dataset patch generation
+and monitoring-subset preparation; see the dataset card.

SHA256SUMS

@@ -0,0 +1 @@
+872e059b1b7bdba0e3c71f5c0472fc6c2d9ceb76a763673a953b74177fca6721  duda-pretrained.tar.gz

continual/SHA256SUMS

@@ -0,0 +1 @@
+6faa51c324f0e058745bc6dc57f0ed60ab8afd46d2cfeafc0876d32b248c4d72  duda-continual-weights.tar.gz

continual/duda-continual-weights.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6faa51c324f0e058745bc6dc57f0ed60ab8afd46d2cfeafc0876d32b248c4d72
+size 519650544

docker/SHA256SUMS

@@ -0,0 +1 @@
+f2520dcaefa212eec292aeea8594c9ed59d2fa141d988afa442e48da62ad91ee  duda-neurips2026.tar.zst

docker/duda-neurips2026.tar.zst

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2520dcaefa212eec292aeea8594c9ed59d2fa141d988afa442e48da62ad91ee
+size 7001249855

docker/image.json

@@ -0,0 +1,12 @@
+{
+  "tag": "duda:neurips2026",
+  "image_id": "sha256:aa6925e15d8491e323ae3466414b5c7b34c747b48a1fc2b5967ed40d785bca3c",
+  "uncompressed_image_bytes": 17418005718,
+  "archive_bytes": 7001249855,
+  "archive_sha256": "f2520dcaefa212eec292aeea8594c9ed59d2fa141d988afa442e48da62ad91ee",
+  "platform": "linux/amd64",
+  "pillow": "11.3.0",
+  "contains_project_code": true,
+  "contains_pretrained_assets": false,
+  "contains_datasets": false
+}

duda-pretrained.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872e059b1b7bdba0e3c71f5c0472fc6c2d9ceb76a763673a953b74177fca6721
+size 202771961

duda-pretrained.tar.gz.sha256

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02265dcccffa889f8e75f3b77c8c283805bed56e1bfb46aabdfccf8385121bbe
+size 89

release.json

@@ -0,0 +1,28 @@
+{
+  "source_commit": "6cc4c68bae235630642da227683456d3b097100f",
+  "model_repo": "ses7720/DUDA",
+  "dataset_repo": "ses7720/DUDA-WRES",
+  "supervised_epoch": 500,
+  "adapted_epoch": 10,
+  "adapted_global_step": 14470,
+  "docker_base": "pytorch/pytorch@sha256:a55ff10111eb11f998884327d37361592e632899edd24fce99886b69289e33e6",
+  "python": "3.11",
+  "torch": "2.4.0",
+  "transformers": "4.56.0",
+  "peft": "0.12.0",
+  "cuda": "12.1",
+  "docker_image": {
+    "path": "docker/duda-neurips2026.tar.zst",
+    "tag": "duda:neurips2026",
+    "image_id": "sha256:aa6925e15d8491e323ae3466414b5c7b34c747b48a1fc2b5967ed40d785bca3c",
+    "uncompressed_image_bytes": 17418005718,
+    "archive_bytes": 7001249855,
+    "archive_sha256": "f2520dcaefa212eec292aeea8594c9ed59d2fa141d988afa442e48da62ad91ee",
+    "platform": "linux/amd64",
+    "pillow": "11.3.0",
+    "contains_project_code": true,
+    "contains_pretrained_assets": false,
+    "contains_datasets": false
+  },
+  "pillow": "11.3.0"
+}