3D 模型识别参考资料

Links

• 2020-Extract-Features-from-3D-meshes-for-Machine-Learning : Two Python scripts for extracting hand crafted features from 3D meshes and point clouds for Machine Learning. Features have been used as data for Random Forests, AdaBoost, Descision Trees, etc.

• 2020-shrec21-3d-mesh-retrieval : Object retrieval and classification networks trained directly on the 3D objects in mesh form.

• 2021-MVTN : The official Pytroch code of ICCV 2021 paper MVTN: Multi-View Transformation Network for 3D Shape Recognition. MVTN learns to transform the rendering parameters of a 3D object to improve the perspectives for better recognition by multi-view netowkrs. Without extra supervision or add loss, MVTN improve the performance in 3D classification and shape retrieval. MVTN achieves state-of-the-art performance on ModelNet40, ShapeNet Core55, and the most recent and realistic ScanObjectNN dataset (up to 6% improvement).

• 2022-3D_STEP_Classification : A new approach for retrieval and classification of 3D models that directly performs in the CAD format without any format conversion to other representations like point clouds of meshes, thus avoiding any loss of information.

• 2022-ROCA : Official code for ROCA: Robust CAD Model Retrieval and Alignment from a Single Image (CVPR 2022)