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
- Trimesh: Trimesh is a pure Python 3.7+ library for loading and using triangular meshes with an emphasis on watertight surfaces. link
- PyMeshLab: PyMeshLab is a Python library that interfaces to MeshLab. link
- Numpy: NumPy is an open source project that enables numerical computing with Python. link
2D Scene Understanding Methods
Depth Estimation
MiDas: Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer. link
Depth Anything V2: Robust and Accurate Depth Estimation for RGB images. link
Metric3D: Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image. link
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second. link
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction. link
Normal Estimation
DSINE: Rethinking Inductive Biases for Surface Normal Estimation. link
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal. link
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction. link
Image Segmentation
OneFormer: One Transformer to Rule Universal Image Segmentation. link
Segment Anything: A promptable segmentation system with zero-shot generalization to unfamiliar objects and images. link
3D Scene Understanding Methods
Mesh Reconstruction
- DUSt3R: Geometric 3D Vision Made Easy. link
Mesh Simplification
- Instant Meshes: Instant Field-Aligned Meshes. link
Object Detection
- UniDet3D: Multi-dataset Indoor 3D Object Detection. link