Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2023 Floor Verhoeven, Tanguy Magne, Olga Sorkine-Hornung
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,151 @@
+---
+license: apache-2.0
+library_name: onnx
+pipeline_tag: image-to-image
+tags:
+  - onnx
+  - document-processing
+  - document-unwarping
+  - image-processing
+  - ocr-preprocessing
+  - computer-vision
+---
+
+# UVDoc Grid Output - Document Unwarping ONNX Model
+
+This is an ONNX export of the [UVDoc](https://github.com/tanguymagne/UVDoc) document unwarping model,
+modified to output a **coordinate grid** instead of an image. This enables high-resolution document
+unwarping via `cv2.remap()`.
+
+## Model Description
+
+UVDoc is a deep learning model for correcting perspective distortion and curvature in photographed
+documents. Unlike the PaddlePaddle ONNX variant that outputs a fixed 288x288 image, this version
+outputs a coordinate mapping grid that can be applied to images of any resolution.
+
+### Key Difference: Grid Output vs Image Output
+
+| Approach | Output | Quality |
+|----------|--------|---------|
+| **Image-output models** | 288x288 RGB image | Poor (must upscale) |
+| **This grid-output model** | 45x31 coordinate grid | Native resolution |
+
+## Model Details
+
+- **Architecture:** UVDoc (ResNet-based encoder-decoder)
+- **Input:** `(1, 3, 720, 496)` - RGB image, normalized [0, 1]
+- **Output:** `(1, 2, 45, 31)` - Coordinate grid in [-1, 1] range
+- **ONNX Opset:** 16
+- **Size:** ~30 MB
+
+### Input Specifications
+
+| Property | Value |
+|----------|-------|
+| Shape | `(batch, 3, 720, 496)` |
+| Format | RGB (not BGR) |
+| Range | `[0, 1]` (normalized) |
+| Layout | NCHW (batch, channels, height, width) |
+
+### Output Specifications
+
+| Property | Value |
+|----------|-------|
+| Shape | `(batch, 2, 45, 31)` |
+| Channels | 2 (x, y coordinates) |
+| Range | `[-1, 1]` (normalized coordinates) |
+| Layout | NCHW (batch, channels, height, width) |
+
+## Usage
+
+### With ONNX Runtime (Python)
+
+```python
+import cv2
+import numpy as np
+import onnxruntime as ort
+
+# Load model
+session = ort.InferenceSession("UVDoc_grid.onnx", providers=['CPUExecutionProvider'])
+
+# Load and preprocess image
+image = cv2.imread("warped_document.jpg")
+h_orig, w_orig = image.shape[:2]
+
+# Prepare model input (720x496 RGB normalized)
+img_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+resized = cv2.resize(img_rgb, (496, 720))  # width, height
+blob = resized.astype(np.float32) / 255.0
+blob = np.transpose(blob, (2, 0, 1))[None]  # (1, 3, 720, 496)
+
+# Run inference
+result = session.run(None, {'image': blob})[0]  # (1, 2, 45, 31)
+
+# Convert grid to remap coordinates
+grid = np.transpose(result[0], (1, 2, 0))  # (45, 31, 2)
+grid_up = cv2.resize(grid, (w_orig, h_orig), interpolation=cv2.INTER_LINEAR)
+
+map_x = ((grid_up[..., 0] + 1) / 2) * (w_orig - 1)
+map_y = ((grid_up[..., 1] + 1) / 2) * (h_orig - 1)
+
+# Apply unwarping to original high-res image
+unwarped = cv2.remap(
+    image,
+    map_x.astype(np.float32),
+    map_y.astype(np.float32),
+    interpolation=cv2.INTER_CUBIC,
+    borderMode=cv2.BORDER_REPLICATE
+)
+
+cv2.imwrite("unwarped_document.jpg", unwarped)
+```
+
+### With HuggingFace Hub
+
+```python
+from huggingface_hub import hf_hub_download
+
+model_path = hf_hub_download(
+    repo_id="YOUR_USERNAME/uvdoc-grid-onnx",
+    filename="UVDoc_grid.onnx"
+)
+```
+
+## Training Details
+
+This model was not retrained. It is a direct ONNX export of the original UVDoc weights from
+[tanguymagne/UVDoc](https://github.com/tanguymagne/UVDoc), with a wrapper to output only the
+2D coordinate grid (discarding the 3D shape output).
+
+### Original Model
+
+- **Paper:** [UVDoc: Neural Grid-based Document Unwarping](https://arxiv.org/abs/2302.02887)
+- **Authors:** Floor Verhoeven, Tanguy Magne, Olga Sorkine-Hornung (ETH Zurich)
+- **Published:** SIGGRAPH Asia 2023
+- **Original Repository:** [tanguymagne/UVDoc](https://github.com/tanguymagne/UVDoc)
+
+## Limitations
+
+- Input must be resized to 720x496 for inference (grid output is always 45x31)
+- Works best on documents with visible text/content (needs features for grid estimation)
+- May not handle extreme perspective distortions well
+- CPU inference takes ~100-200ms per image
+
+## Citation
+
+If you use this model, please cite the original UVDoc paper:
+
+```bibtex
+@inproceedings{UVDoc,
+    title={{UVDoc}: Neural Grid-based Document Unwarping},
+    author={Floor Verhoeven and Tanguy Magne and Olga Sorkine-Hornung},
+    booktitle = {SIGGRAPH ASIA, Technical Papers},
+    year = {2023},
+    url={https://doi.org/10.1145/3610548.3618174}
+}
+```
+
+## License
+
+This ONNX export is provided under the Apache 2.0 license. The original UVDoc model is also
+Apache 2.0 licensed. See the original repository for full license details.

config.json

@@ -0,0 +1,33 @@
+{
+  "model_type": "uvdoc",
+  "architecture": "encoder-decoder",
+  "framework": "onnx",
+  "input": {
+    "name": "image",
+    "shape": [1, 3, 720, 496],
+    "format": "NCHW",
+    "dtype": "float32",
+    "color_space": "RGB",
+    "normalization": {
+      "range": [0, 1],
+      "method": "divide_by_255"
+    }
+  },
+  "output": {
+    "name": "grid_2d",
+    "shape": [1, 2, 45, 31],
+    "format": "NCHW",
+    "dtype": "float32",
+    "description": "2D coordinate grid for document unwarping",
+    "coordinate_range": [-1, 1]
+  },
+  "onnx_opset": 16,
+  "original_model": {
+    "name": "UVDoc",
+    "repository": "https://github.com/tanguymagne/UVDoc",
+    "paper": "https://arxiv.org/abs/2302.02887",
+    "authors": ["Floor Verhoeven", "Tanguy Magne", "Olga Sorkine-Hornung"],
+    "institution": "ETH Zurich",
+    "venue": "SIGGRAPH Asia 2023"
+  }
+}

example.py

@@ -0,0 +1,235 @@
+#!/usr/bin/env python3
+"""
+UVDoc Grid-Output Document Unwarping Example
+
+This script demonstrates how to use the UVDoc ONNX model with grid output
+for high-resolution document unwarping.
+
+The key advantage of this grid-output model over image-output models is that
+the coordinate grid can be upscaled to any resolution, preserving document
+quality when applied via cv2.remap().
+
+Usage:
+    python example.py input_image.jpg output_image.jpg
+    python example.py input_image.jpg output_image.jpg --model path/to/UVDoc_grid.onnx
+
+Requirements:
+    pip install onnxruntime opencv-python numpy
+
+Optional (for automatic model download):
+    pip install huggingface_hub
+"""
+
+import argparse
+import sys
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+# Model input dimensions (fixed for UVDoc architecture)
+MODEL_INPUT_HEIGHT = 720
+MODEL_INPUT_WIDTH = 496
+
+
+def load_model(model_path: str = None):
+    """
+    Load the ONNX model.
+
+    Args:
+        model_path: Path to the ONNX model file. If None, attempts to download
+                    from HuggingFace Hub.
+
+    Returns:
+        ONNX Runtime InferenceSession
+    """
+    import onnxruntime as ort
+
+    if model_path is None:
+        try:
+            from huggingface_hub import hf_hub_download
+
+            print("Downloading model from HuggingFace Hub...")
+            model_path = hf_hub_download(
+                repo_id="YOUR_USERNAME/uvdoc-grid-onnx",  # Update with actual repo
+                filename="UVDoc_grid.onnx"
+            )
+            print(f"Model downloaded to: {model_path}")
+        except ImportError:
+            print("Error: huggingface_hub not installed. Install it or provide --model path.")
+            print("  pip install huggingface_hub")
+            sys.exit(1)
+
+    print(f"Loading model from: {model_path}")
+    session = ort.InferenceSession(
+        model_path,
+        providers=['CPUExecutionProvider']
+    )
+
+    return session
+
+
+def preprocess_image(image: np.ndarray) -> np.ndarray:
+    """
+    Preprocess image for UVDoc model input.
+
+    Args:
+        image: BGR image from cv2.imread()
+
+    Returns:
+        Preprocessed tensor of shape (1, 3, 720, 496)
+    """
+    # Convert BGR to RGB
+    img_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+    # Resize to model input size
+    resized = cv2.resize(img_rgb, (MODEL_INPUT_WIDTH, MODEL_INPUT_HEIGHT))
+
+    # Normalize to [0, 1]
+    normalized = resized.astype(np.float32) / 255.0
+
+    # Convert HWC to CHW format
+    transposed = np.transpose(normalized, (2, 0, 1))
+
+    # Add batch dimension
+    batched = np.expand_dims(transposed, axis=0)
+
+    return batched
+
+
+def apply_grid_unwarping(
+    image: np.ndarray,
+    grid: np.ndarray,
+    interpolation: int = cv2.INTER_CUBIC
+) -> np.ndarray:
+    """
+    Apply the coordinate grid to unwarp the image.
+
+    Args:
+        image: Original BGR image (any resolution)
+        grid: Model output grid of shape (1, 2, 45, 31)
+        interpolation: OpenCV interpolation method
+
+    Returns:
+        Unwarped image at original resolution
+    """
+    h_orig, w_orig = image.shape[:2]
+
+    # Remove batch dimension and transpose to (H, W, 2)
+    grid_2d = np.transpose(grid[0], (1, 2, 0))  # (45, 31, 2)
+
+    # Upscale grid to original image resolution
+    grid_upscaled = cv2.resize(
+        grid_2d,
+        (w_orig, h_orig),
+        interpolation=cv2.INTER_LINEAR
+    )
+
+    # Convert normalized coordinates [-1, 1] to pixel coordinates
+    # Grid channel 0 = x (width), channel 1 = y (height)
+    map_x = ((grid_upscaled[..., 0] + 1) / 2) * (w_orig - 1)
+    map_y = ((grid_upscaled[..., 1] + 1) / 2) * (h_orig - 1)
+
+    # Apply remapping
+    unwarped = cv2.remap(
+        image,
+        map_x.astype(np.float32),
+        map_y.astype(np.float32),
+        interpolation=interpolation,
+        borderMode=cv2.BORDER_REPLICATE
+    )
+
+    return unwarped
+
+
+def unwarp_document(
+    image_path: str,
+    output_path: str,
+    model_path: str = None
+) -> None:
+    """
+    Main function to unwarp a document image.
+
+    Args:
+        image_path: Path to input warped document image
+        output_path: Path to save unwarped result
+        model_path: Optional path to ONNX model file
+    """
+    # Load image
+    print(f"Loading image: {image_path}")
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Could not load image from {image_path}")
+        sys.exit(1)
+
+    h, w = image.shape[:2]
+    print(f"Image size: {w}x{h}")
+
+    # Load model
+    session = load_model(model_path)
+
+    # Get input name
+    input_name = session.get_inputs()[0].name
+    print(f"Model input name: {input_name}")
+
+    # Preprocess
+    print("Preprocessing image...")
+    input_tensor = preprocess_image(image)
+    print(f"Input tensor shape: {input_tensor.shape}")
+
+    # Run inference
+    print("Running inference...")
+    result = session.run(None, {input_name: input_tensor})[0]
+    print(f"Output grid shape: {result.shape}")
+    print(f"Output grid range: [{result.min():.4f}, {result.max():.4f}]")
+
+    # Apply unwarping
+    print("Applying grid-based unwarping...")
+    unwarped = apply_grid_unwarping(image, result)
+
+    # Save result
+    print(f"Saving result to: {output_path}")
+    cv2.imwrite(output_path, unwarped)
+
+    print("Done!")
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Unwarp document images using UVDoc grid-output ONNX model",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+    python example.py warped_doc.jpg unwarped_doc.jpg
+    python example.py warped_doc.jpg unwarped_doc.jpg --model UVDoc_grid.onnx
+        """
+    )
+
+    parser.add_argument(
+        "input",
+        help="Path to input warped document image"
+    )
+
+    parser.add_argument(
+        "output",
+        help="Path to save unwarped output image"
+    )
+
+    parser.add_argument(
+        "--model", "-m",
+        default=None,
+        help="Path to UVDoc_grid.onnx model file (downloads from HuggingFace if not provided)"
+    )
+
+    args = parser.parse_args()
+
+    # Validate input file exists
+    if not Path(args.input).exists():
+        print(f"Error: Input file not found: {args.input}")
+        sys.exit(1)
+
+    unwarp_document(args.input, args.output, args.model)
+
+
+if __name__ == "__main__":
+    main()