paper-with-me

홈 › Papers

CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds

2021-08-31 · ICCV 2021 10 · Eric-Tuan Lê, Minhyuk Sung, Duygu Ceylan, Radomir Mech, Tamy Boubekeur, Niloy J. Mitra

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%.

📄 PDF Abstract BibTeX arXiv:2109.00113

Code (1)

erictuanle/cpfn 공식 구현 pytorch

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations

2026-08-20 · En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng 외 arxiv

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 Recommendation

DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds

2025-03-24 · CVPR 2025 1 · Youyu Chen, Junjun Jiang, Kui Jiang, Xiao Tang 외

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…

3DGSScheduling

BPNet: Bézier Primitive Segmentation on 3D Point Clouds

2023-07-08 · Rao Fu, Cheng Wen, Qian Li, Xiao Xiao 외

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 SegmentationSegmentation

Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals

2026-06-18 · Shravan Talupula, Saurabh Sharma arxiv

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

2024-03-09 · Yanyi Zhang, Qi Jia, Xin Fan, Yu Liu 외

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