scenezoo 0.1.0__tar.gz

scenezoo-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.

scenezoo-0.1.0/PKG-INFO

@@ -0,0 +1,270 @@
+Metadata-Version: 2.4
+Name: scenezoo
+Version: 0.1.0
+Summary: Read 3D indoor-scene datasets (ScanNet, ScanNet++, ARKitScenes, Matterport3D, ...) through one Python API.
+Author: Yiming Zhang
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/eamonn-zh/scenezoo
+Project-URL: Repository, https://github.com/eamonn-zh/scenezoo
+Project-URL: Documentation, https://scenezoo.readthedocs.io/en/latest/
+Project-URL: Issues, https://github.com/eamonn-zh/scenezoo/issues
+Keywords: 3D vision,3D scenes,datasets,RGB-D,point clouds,ScanNet
+Classifier: Natural Language :: English
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fsspec[http]>=2023.1
+Requires-Dist: numpy>=1.23
+Requires-Dist: av>=15
+Requires-Dist: cachetools>=5.3
+Requires-Dist: lz4>=3.1
+Requires-Dist: open3d>=0.19.0
+Requires-Dist: plyfile
+Requires-Dist: pandas>=2.0
+Requires-Dist: Pillow>=9.1
+Requires-Dist: scipy>=1.9
+Provides-Extra: render
+Requires-Dist: torch; extra == "render"
+Provides-Extra: dev
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: ruff<0.13,>=0.12; extra == "dev"
+Dynamic: license-file
+
+# scenezoo
+
+[![PyPI](https://img.shields.io/pypi/v/scenezoo)](https://pypi.org/project/scenezoo/)
+[![Documentation](https://readthedocs.org/projects/scenezoo/badge/?version=latest)](https://scenezoo.readthedocs.io/en/latest/)
+[![CI](https://github.com/eamonn-zh/scenezoo/actions/workflows/ci.yml/badge.svg)](https://github.com/eamonn-zh/scenezoo/actions/workflows/ci.yml)
+
+**scenezoo** reads popular 3D indoor-scene datasets through one Python API.
+Point it at a dataset you have downloaded, and get meshes, point clouds,
+segmentation labels, 3D boxes, and synchronized RGB-D frames with cameras as
+NumPy arrays and Open3D objects, without writing a new loader for every
+dataset.
+
+**Documentation: <https://scenezoo.readthedocs.io/en/latest/>.** Start with the [quick start](https://scenezoo.readthedocs.io/en/latest/get_started/quickstart.html),
+browse the [examples](https://scenezoo.readthedocs.io/en/latest/examples/index.html), or look up a
+[dataset](https://scenezoo.readthedocs.io/en/latest/datasets/index.html).
+
+## Installation
+
+scenezoo supports Python 3.10 to 3.14.
+
+```bash
+pip install scenezoo
+```
+
+For development, clone the repository and install it in editable mode with the
+test tools:
+
+```bash
+git clone https://github.com/eamonn-zh/scenezoo.git
+cd scenezoo
+pip install -e ".[dev]"
+```
+
+Video frame sources (ARKitScenes MOV, MultiScan, and ScanNet++ iPhone captures)
+are decoded frame-exactly with [PyAV](https://github.com/PyAV-Org/PyAV), whose
+wheels bundle FFmpeg; no system `ffmpeg` installation is needed.
+
+## Unified API
+
+```python
+from scenezoo import get_dataset, get_dataset_info, list_datasets
+
+dataset = get_dataset("scannetv2", "/path/to/scannet")
+scene_id = dataset.get_ids("val")[0]
+
+if dataset.supports("mesh"):
+    mesh = dataset.get_mesh(scene_id)
+
+if dataset.supports("points"):
+    points = dataset.get_points(scene_id)
+
+if dataset.supports("segmentation"):
+    segmentation = dataset.get_segmentation(scene_id)
+    print(segmentation.domain, segmentation.labels.shape)
+
+if dataset.supports("boxes"):
+    boxes_by_id, id_to_name = dataset.get_boxes(scene_id)
+
+if dataset.supports("frames"):
+    frames = dataset.get_frames(
+        scene_id,
+        step=30,
+        items=("rgb", "depth", "rgb_intrinsics", "world_to_camera"),
+        output_size=(640, 480),
+        center_crop=True,
+    )
+
+print(list_datasets())
+print(get_dataset_info("scannetv2"))  # canonical release metadata
+```
+
+`list_datasets()` and `get_dataset_info()` use a static built-in catalog, so
+they do not import Open3D, OpenCV, video decoders, or adapter modules. Inspect
+`get_dataset_info(name).spec` for operations, mesh/box/label variants, and frame
+sources. Accessing `.dataset_class` or calling `get_dataset()` intentionally
+loads only the selected adapter. The `scenezoo.io` and `scenezoo.ops`
+namespaces also resolve re-exported helpers lazily, so importing cache or frame
+utilities does not initialize unrelated video, annotation, or geometry runtimes.
+
+The seven common dataset calls are:
+
+- `check(*, sample_ids=None, require_complete=False, raise_on_error=False)`
+- `get_ids(split)`
+- `get_mesh(sample_id, *, mesh_type=None)`
+- `get_points(sample_id)`
+- `get_segmentation(sample_id)`
+- `get_boxes(sample_id, *, box_type=...)`
+- `get_frames(sample_id, *, indices=None, step=1, items=..., output_size=None, center_crop=False, rotate_to_up=True)`
+
+Unsupported operations and unsupported frame items raise
+`UnsupportedOperationError`. Unknown operation names, frame item names, and
+invalid argument combinations raise `ValueError`.
+
+## Check a download before using it
+
+Dataset checking is explicit and never runs during construction or normal data
+access. It checks paths and file groups without decoding meshes, images, or
+videos:
+
+```python
+dataset = get_dataset("scannetv2", "/path/to/scannet", offline=True)
+report = dataset.check()
+print(report)
+
+# Check only the scenes a job is about to use. Missing requested IDs are errors.
+focused = dataset.check(sample_ids=("scene0000_00", "scene0001_00"))
+
+# Treat every missing ID from the official splits as an error and raise once.
+dataset.check(require_complete=True, raise_on_error=True)
+```
+
+`DatasetCheckReport` exposes `ok`, `errors`, `warnings`, `issues`, and `stats`.
+Each `CheckIssue` contains a severity, stable code, explanation, relevant path,
+expected layout, and suggested action. An intentionally partial download reports
+missing split scenes as warnings by default; explicitly requested scenes are
+always required. `raise_on_error=True` raises `DatasetCheckError` carrying the
+same report.
+
+The checkers understand each release's archive policy. ScanNet, ScanNet++,
+ARKitScenes, MultiScan, ASE, Matterport3D, Structured3D, S3DIS, and SceneNN need
+their download archives extracted. ScanNet keeps its official 2D annotation
+ZIPs, while 3RScan keeps each native `sequence.zip` sensor stream compressed.
+
+## Return semantics
+
+`get_points()` returns a `PointBatch`. Its `xyz` array is always `float32` with
+shape `(N, 3)`; optional RGB, normals, semantic/instance labels, and source-view
+provenance are row-aligned. Call `to_point_cloud()` only when an Open3D object
+is needed.
+
+`get_segmentation()` returns `Segmentation3D` with `labels`, `id_to_name`,
+`domain` (`"point"`, `"vertex"`, or `"face"`), and `invalid_id`.
+
+`get_boxes()` always returns `(boxes_by_id, id_to_name)`.
+
+`get_frames()` returns a slot-based `FrameBatch`. `indices` are original video
+frame numbers (or stable source positions for filename-only captures), and
+`frame_keys` retains source names such as DSLR filenames. `source_frame_count`
+is the source sequence length. Every requested per-frame field has `N` as its
+first dimension, including constant intrinsics, which are expanded to
+`(N, 3, 3)`.
+
+The frame conventions are intentionally strict:
+
+- depth is `float32` in metres; missing, negative, and non-finite values are `0.0`;
+- extrinsics are OpenCV-style `world_to_camera` matrices with shape `(N, 4, 4)`;
+- pixel coordinates follow OpenCV: integer coordinates are pixel centres;
+- RGB, albedo, depth, normal/instance/semantic/confidence maps, and intrinsics use the same resize/crop transform;
+- `rotate_to_up=True` rotates pixels by a right angle and applies the equivalent camera roll to `world_to_camera`, so intrinsics always stay upper-triangular pinhole matrices;
+- RGB uses high-quality interpolation, while depth and discrete maps use nearest-neighbor;
+- explicit `indices` preserve the requested order and cannot be combined with `step != 1`;
+- default sampling filters frames with invalid camera matrices before applying `step`.
+
+Adapters for non-pinhole captures additionally return `camera_model`,
+`distortion`, and `image_sizes`. ScanNet++ uses these fields for its
+`OPENCV_FISHEYE`, `OPENCV`, `PINHOLE`, and `EQUIRECTANGULAR` sources instead of
+discarding the source camera model.
+
+## Built-in datasets
+
+| Canonical name | Aliases | Mesh | Points | Segmentation | Boxes | Frames |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| [`scannetv2`](https://scenezoo.readthedocs.io/en/latest/datasets/scannet.html) | `scannet` | raw/decimated/semantic | no | instance + NYU40, vertex | yes | RGB-D, camera, 2D labels, timestamps, IMU |
+| [`scannetppv2`](https://scenezoo.readthedocs.io/en/latest/datasets/scannetpp.html) | `scannet++`, `scannetpp`, `scannet++v2` | yes | laser scan | vertex, multilabel | yes | iPhone, DSLR, panorama |
+| [`arkitscenes`](https://scenezoo.readthedocs.io/en/latest/datasets/arkitscenes.html) | — | yes | no | vertex (box-derived) | yes | multi-source RGB-D, confidence |
+| [`multiscan`](https://scenezoo.readthedocs.io/en/latest/datasets/multiscan.html) | — | PLY/textured | no | object/part instance + semantic, face | yes | RGB-D, confidence, camera metadata |
+| [`ase`](https://scenezoo.readthedocs.io/en/latest/datasets/ase.html) | `aria-ase`, `aria-synthetic-environments` | no | semi-dense SLAM points | no | wall/door/window layout OBB | fisheye RGB, ray-depth, instances, poses |
+| [`3rscan`](https://scenezoo.readthedocs.io/en/latest/datasets/3rscan.html) | `threerscan` | textured/instance | no | instance + Global/NYU40/Eigen13/RIO27/RIO7, vertex | yes | RGB-D and camera |
+| [`s3dis`](https://scenezoo.readthedocs.io/en/latest/datasets/s3dis.html) | `stanford3d`, `stanford-3d` | no | XYZRGB + labels | instance + 13-class semantic, point | yes | no |
+| [`matterport3d`](https://scenezoo.readthedocs.io/en/latest/datasets/matterport3d.html) | — | textured/house/region/Poisson | no | instance + semantic, face | official OBB | raw + undistorted RGB-D |
+| [`scenenn`](https://scenezoo.readthedocs.io/en/latest/datasets/scenenn.html) | — | yes | no | vertex | no | no |
+| [`structured3d`](https://scenezoo.readthedocs.io/en/latest/datasets/structured3d.html) | `structure3d` | reconstructed room layout | RGB-D fusion | semantic + instance, point | official OBB | perspective + panorama RGB-D and labels |
+
+Each dataset page linked above documents the expected download layout,
+dataset-specific options (label spaces, capture sources, region and room
+selectors), and extra methods such as calibration, IMU, and scene metadata.
+
+## Registering an adapter
+
+Registration is atomic: the canonical name and all aliases are checked for
+conflicts before any entry is added.
+
+```python
+from scenezoo import Dataset, register_dataset
+
+
+@register_dataset("my-scenes", aliases=("mine",))
+class MyScenes(Dataset):
+    def _load_splits(self):
+        return {"train": ["scene-001"]}
+
+    def _load_metadata(self):
+        return {"coordinate_system": "z-up"}
+
+    def get_mesh(self, sample_id, *, mesh_type=None):
+        return load_my_mesh(self.root_dir / sample_id)
+```
+
+`splits` and `metadata` are lazy `cached_property` values. Implement only the
+standard methods backed reliably by the dataset; `supports()` detects overridden
+methods automatically. Adapter constructors should use explicit keyword
+parameters rather than a catch-all `**kwargs`. Custom adapters may override the
+protected `_check()` hook to add source-specific layout diagnostics; normal users
+call only `dataset.check()`.
+
+## Cache and offline mode
+
+Remote split and metadata files are cached under `SCENEZOO_CACHE_DIR` (or
+`~/.cache/scenezoo`). Pass `offline=True` to forbid network access while allowing
+previously cached remote files to be reused.
+
+## Development
+
+```bash
+pip install -e ".[dev]" -r docs/requirements.txt
+PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 pytest
+ruff check src test && ruff format --check src test
+python -m sphinx -W -b html docs docs/_build/html
+```
+
+Real-data integration tests are opt-in through `SCENEZOO_TEST_*_ROOT` environment
+variables; no dataset path is embedded in the test suite. The
+documentation is built from [`docs/`](https://github.com/eamonn-zh/scenezoo/tree/main/docs) and published at
+<https://scenezoo.readthedocs.io/en/latest/>.
+
+## License
+
+See [LICENSE](https://github.com/eamonn-zh/scenezoo/blob/main/LICENSE).