CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds
Representing human-made objects as a collection of base primitives has a long history in computer vision and reverse engineering. In the case of high-resolution point cloud scans, the challenge is to be able to detect both large primitives as well as those explaining the detailed parts. While the classical RANSAC approach requires case-specific parameter tuning, state-of-the-art networks are limited by memory consumption of their backbone modules such as PointNet++, and hence fail to detect the fine-scale primitives. We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks. As a key enabler, we present a merging formulation that dynamically aggregates the primitives across global and local scales. Our evaluation demonstrates that CPFN improves the state-of-the-art SPFN performance by 13-14% on high-resolution point cloud datasets and specifically improves the detection of fine-scale primitives by 20-22%.
Code (1)
Tasks
Vocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations
We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, …
Sequential RecommendationDashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
3D Gaussian Splatting (3DGS) renders pixels by rasterizing Gaussian primitives, where the rendering resolution and the primitive number, concluded as the optimization complexity, dominate the time cost in primitive optim…
3DGSSchedulingBPNet: Bézier Primitive Segmentation on 3D Point Clouds
This paper proposes BPNet, a novel end-to-end deep learning framework to learn B\'ezier primitive segmentation on 3D point clouds. The existing works treat different primitive types separately, thus limiting them to fini…
Point Cloud SegmentationSegmentationTemporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals
Estimating causal effects in industrial time series requires handling temporal dynamics, time-varying treatments, and unobserved confounders. Existing causal foundation models (CausalPFN, CausalFM) operate only on static…
CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning
Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods…
AttributeCompositional Zero-Shot LearningDisentanglementObject+2