| # Acknowledgments | |
| **PySceneKit** would not be possible without the incredible work of various open-source projects and libraries that have paved the way for scene processing and visualization. I want to extend my heartfelt thanks to: | |
| ## Libraries | |
| - **Open3D**: A modern library for 3D data processing. [link](https://www.open3d.org/) | |
| - **Trimesh**: Trimesh is a pure Python 3.7+ library for loading and using triangular meshes with an emphasis on watertight surfaces. [link](https://trimesh.org/) | |
| - **PyMeshLab**: PyMeshLab is a Python library that interfaces to MeshLab. [link](https://pymeshlab.readthedocs.io/en/latest/) | |
| - **Numpy**: NumPy is an open source project that enables numerical computing with Python. [link](https://numpy.org/) | |
| ## 2D Scene Understanding Methods | |
| ### Depth Estimation | |
| - **MiDas**: Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer. [link](https://github.com/isl-org/MiDaS) | |
| - **Depth Anything V2**: Robust and Accurate Depth Estimation for RGB images. [link](https://github.com/DepthAnything/Depth-Anything-V2) | |
| - **Metric3D**: Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image. [link](https://github.com/YvanYin/Metric3D) | |
| - **Depth Pro**: Sharp Monocular Metric Depth in Less Than a Second. [link](https://github.com/apple/ml-depth-pro) | |
| - **Lotus**: Diffusion-based Visual Foundation Model for High-quality Dense Prediction. [link](https://github.com/EnVision-Research/Lotus) | |
| ### Normal Estimation | |
| - **DSINE**: Rethinking Inductive Biases for Surface Normal Estimation. [link](https://baegwangbin.github.io/DSINE/) | |
| - **StableNormal**: Reducing Diffusion Variance for Stable and Sharp Normal. [link](https://github.com/Stable-X/StableNormal) | |
| - **Lotus**: Diffusion-based Visual Foundation Model for High-quality Dense Prediction. [link](https://github.com/EnVision-Research/Lotus) | |
| ### Image Segmentation | |
| - **OneFormer**: One Transformer to Rule Universal Image Segmentation. [link](https://github.com/SHI-Labs/OneFormer) | |
| - **Segment Anything**: A promptable segmentation system with zero-shot generalization to unfamiliar objects and images. [link](https://github.com/facebookresearch/segment-anything) | |
| ## 3D Scene Understanding Methods | |
| ### Mesh Reconstruction | |
| - **DUSt3R**: Geometric 3D Vision Made Easy. [link](https://dust3r.europe.naverlabs.com/) | |
| ### Mesh Simplification | |
| - **Instant Meshes**: Instant Field-Aligned Meshes. [link](https://github.com/wjakob/instant-meshes) | |
| ### Object Detection | |
| - **UniDet3D**: Multi-dataset Indoor 3D Object Detection. [link](https://github.com/3dlg-hcvc/unidet3d) | |