docs

.gitattributes

@@ -1,35 +1,6 @@
-*.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
+# Git LFS for large model files
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.mlpackage 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
+*.weight.bin 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

.gitignore

@@ -0,0 +1,9 @@
+__pycache__/
+*.pyc
+*.pyo
+*.egg-info/
+dist/
+build/
+.eggs/
+*.egg
+.DS_Store

README.md

@@ -1,3 +1,150 @@
----
-license: mit
----
+---
+license: mit
+tags:
+  - coreml
+  - depth-estimation
+  - computer-vision
+  - ios
+  - macos
+  - panorama
+  - vision
+pipeline_tag: depth-estimation
+base_model: Insta360-Research/DAP-weights
+tags:
+  - coreml
+  - monocular-depth-estimation
+  - panorama-depth-estimation
+---
+
+# DAP CoreML — Panoramic Depth Estimation for Apple Silicon
+
+CoreML export of **[DAP (Depth Any Panoramas)](https://github.com/Insta360-Research-Team/DAP)**, a foundation model for monocular depth estimation on equirectangular 360° panoramas. Optimized for on-device inference on iOS 18+ and macOS with Apple Silicon.
+
+| | |
+|---|---|
+| **Original model** | [DAP (Insta360 Research)](https://huggingface.co/Insta360-Research/DAP-weights) |
+| **Architecture** | Depth-Anything-V2 + DINOv3 (ViT-L) |
+| **Input** | Equirectangular panorama, 2:1 aspect ratio (default 1024×512) |
+| **Output** | Monocular depth map, float32, same resolution as input |
+| **CoreML size** | ~1.2 GB |
+| **Deployment** | iOS 18+, macOS 15+ (Apple Silicon) |
+
+## Validation
+
+Exported and validated against PyTorch ground truth:
+
+| Metric | Value |
+|---|---|
+| Max absolute difference | 5.54×10⁻⁶ |
+| Mean absolute difference | 4.50×10⁻⁷ |
+| Correlation | 1.000000 |
+| CoreML inference (M-series) | ~650 ms |
+
+![Validation](test_output/comparison.png)
+
+## Quick Start — CLI (macOS)
+
+Compile and run `DepthPredictor.swift` as a standalone tool — no Xcode project needed:
+
+```bash
+# Compile
+swiftc -O -o depth_predictor DepthPredictor.swift \
+    -framework CoreML -framework Vision -framework CoreImage \
+    -framework CoreGraphics -framework AppKit
+
+# Generate a 16-bit grayscale depth map
+./depth_predictor -m DAPModel.mlpackage -i panorama.jpg -o depth.png
+
+# Colorized with jet colormap
+./depth_predictor -m DAPModel.mlpackage -i panorama.jpg -o depth.png -c jet
+
+# Turbo colormap
+./depth_predictor -m DAPModel.mlpackage -i panorama.jpg -o depth.png -c turbo
+```
+
+Options:
+
+| Flag | Description |
+|---|---|
+| `-m, --model PATH` | Path to `DAPModel.mlpackage` or `.mlmodelc` |
+| `-i, --input PATH` | Input equirectangular panorama (2:1 aspect ratio) |
+| `-o, --output PATH` | Output PNG file |
+| `-c, --colormap STYLE` | `grayscale` (16-bit, default), `jet`, or `turbo` |
+
+The model is automatically compiled on first use and cached for subsequent runs.
+
+## Quick Start — Xcode (iOS / macOS)
+
+Add `DAPModel.mlpackage` to your Xcode project (Xcode auto-generates the `DAPModel` Swift class), then use the included `DepthPredictor.swift`:
+
+```swift
+import Foundation
+import CoreML
+import Vision
+import CoreImage
+
+// Load the model from a .mlpackage URL
+let modelURL = Bundle.main.url(forResource: "DAPModel", withExtension: "mlpackage")!
+let predictor = DepthPredictor(modelURL: modelURL)
+
+// Run inference on a CGImage (equirectangular panorama)
+predictor.predictDepth(from: cgImage) { depth in
+    guard let depth = depth else { return }
+    // `depth` is a DepthResult with raw Float32 values and a CIImage
+
+    // Colorize with jet colormap
+    let colorized = predictor.applyJetColormap(to: depth)
+
+    // Or access raw depth values directly
+    let values = depth.getDepthValues()  // [Float32], row-major
+}
+```
+
+## Files
+
+| File | Description |
+|---|---|
+| `DAPModel.mlpackage/` | CoreML model (depth-only, ImageType input) |
+| `model.pth` | Original DAP PyTorch weights |
+| `export_and_validate_coreml.py` | Export + validation script |
+| `DepthPredictor.swift` | Swift inference wrapper |
+| `depth_anything_utils.py` | Image preprocessing utilities |
+| `networks/` | DAP model definition |
+| `depth_anything_v2_metric/` | Depth-Anything-V2 + DINOv3 backbone |
+| `test/test.png` | Test panorama for validation |
+| `test_output/` | PyTorch vs CoreML comparison |
+
+## Export from Scratch
+
+Reproduce the CoreML model from the PyTorch weights:
+
+```bash
+# Install dependencies
+pip install -r requirements.txt
+
+# Export and validate (produces DAPModel.mlpackage + test_output/)
+python export_and_validate_coreml.py
+
+# Custom resolution (must be multiples of 16)
+python export_and_validate_coreml.py --height 768 --width 1536
+
+# Skip export, only validate existing model
+python export_and_validate_coreml.py --skip_export
+```
+
+## Citation
+
+```bibtex
+@article{lin2025dap,
+  title={Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation},
+  author={Lin, Xin and Song, Meixi and Zhang, Dizhe and Lu, Wenxuan and Li, Haodong and Du, Bo and Yang, Ming-Hsuan and Nguyen, Truong and Qi, Lu},
+  journal={arXiv},
+  year={2025}
+}
+```
+
+## License
+
+Original DAP weights and model architecture: **MIT** ([Insta360 Research Team](https://github.com/Insta360-Research-Team/DAP))
+
+CoreML export and Swift wrapper: **MIT**