Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: javrtg/AnyCalib
+tags:
+  - mlx
+  - camera-calibration
+  - swift
+library_name: mlx
+pipeline_tag: image-feature-extraction
+---
+
+# AnyCalib — MLX weights
+
+Converted weights for [mlx-swift-AnyCalib](https://github.com/mnmly/mlx-swift-AnyCalib), a Swift/MLX port of
+[AnyCalib](https://github.com/javrtg/AnyCalib) (Tirado-Garín & Civera, ICCV 2025):
+single-view camera calibration with a camera model chosen after the network runs.
+
+These are **not** new weights. They are the official AnyCalib checkpoints in a
+different container.
+
+## What was changed
+
+* Repacked from PyTorch `.pt` into `safetensors`.
+* Convolution tensors transposed `(out, in, kH, kW) → (out, kH, kW, in)` for MLX's
+  native NHWC layout. That same rule also reshapes the `(1, 3, 1, 1)` ImageNet
+  mean/std buffers to `(1, 1, 1, 3)`.
+* Optionally cast to `float16`; the default build is `float32`.
+
+No weight *values* are altered beyond that optional cast. The port is verified
+stage by stage against the PyTorch reference — on MLX's CPU backend every stage
+matches to within float32's own noise floor (ray field within 0.0003°).
+
+## Layout
+
+One subdirectory per pretrained variant, each holding `config.json` and
+`weights.safetensors`:
+
+```
+anycalib_dist/
+anycalib_edit/
+anycalib_gen/
+anycalib_pinhole/
+```
+
+The variants differ only in training imagery: `pinhole` (perspective only),
+`gen` (perspective + distorted), `dist` (distorted + strongly distorted),
+`edit` (stretched and cropped perspective).
+
+## Usage
+
+```bash
+anycalib calibrate photo.jpg --cam pinhole --repo mnmly/anycalib-mlx
+```
+
+The Swift loader resolves these through the shared Hugging Face cache, so a copy
+pulled by `huggingface_hub` is reused and vice versa.
+
+## License and attribution
+
+Apache 2.0, inherited from upstream. See `LICENSE` and `NOTICE` in this repo.
+
+Original work © Javier Tirado-Garín and Javier Civera, I3A, University of
+Zaragoza. The backbone is DINOv2, © Meta Platforms, Inc., also Apache 2.0.
+
+```bibtex
+@InProceedings{tirado2025anycalib,
+  author={Javier Tirado-Gar{\'i}n and Javier Civera},
+  title={{AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration}},
+  booktitle={ICCV},
+  year={2025}
+}
+```