Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918204788441088 |
|---|---|
| author | Ma, Xinzhu Wang, Cheng Tang, Chen Wang, Bin Tang, Shixiang Meng, Yuan Wang, Yunhong Huang, Di |
| author_facet | Ma, Xinzhu Wang, Cheng Tang, Chen Wang, Bin Tang, Shixiang Meng, Yuan Wang, Yunhong Huang, Di |
| contents | Recovering CAD models from point clouds requires reconstructing their topology and sketch-based extrusion primitives. A dominant paradigm for representing sketches involves implicit neural representations such as Signed Distance Fields (SDFs). However, this indirect approach inherently struggles with precision, leading to unintended curved edges and models that are difficult to edit. In this paper, we propose Point2Primitive, a framework that learns to directly predict the explicit, parametric primitives of CAD models. Our method treats sketch reconstruction as a set prediction problem, employing a improved transformer-based decoder with explicit position queries to directly detect and predict the fundamental sketch curves (i.e., type and parameter) from the point cloud. Instead of approximating a continuous field, we formulate curve parameters as explicit position queries, which are optimized autoregressively to achieve high accuracy. The overall topology is rebuilt via extrusion segmentation. Extensive experiments demonstrate that this direct prediction paradigm significantly outperforms implicit methods in both primitive accuracy and overall geometric fidelity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02043 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction Ma, Xinzhu Wang, Cheng Tang, Chen Wang, Bin Tang, Shixiang Meng, Yuan Wang, Yunhong Huang, Di Computer Vision and Pattern Recognition Recovering CAD models from point clouds requires reconstructing their topology and sketch-based extrusion primitives. A dominant paradigm for representing sketches involves implicit neural representations such as Signed Distance Fields (SDFs). However, this indirect approach inherently struggles with precision, leading to unintended curved edges and models that are difficult to edit. In this paper, we propose Point2Primitive, a framework that learns to directly predict the explicit, parametric primitives of CAD models. Our method treats sketch reconstruction as a set prediction problem, employing a improved transformer-based decoder with explicit position queries to directly detect and predict the fundamental sketch curves (i.e., type and parameter) from the point cloud. Instead of approximating a continuous field, we formulate curve parameters as explicit position queries, which are optimized autoregressively to achieve high accuracy. The overall topology is rebuilt via extrusion segmentation. Extensive experiments demonstrate that this direct prediction paradigm significantly outperforms implicit methods in both primitive accuracy and overall geometric fidelity. |
| title | Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.02043 |