Le, Eric-Tuan; Sung, Minhyuk; Ceylan, Duygu; Mech, Radomir; Boubekeur, Tamy; Mitra, Niloy J; (2022) CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds. In: 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021). (pp. pp. 7437-7446). IEEE: Montreal, QC, Canada.

Preview

PDF cpfn.pdf - Accepted Version Download (14MB) | Preview

Abstract

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++ [27], 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%. Our code is available at: https://github.com/erictuanle/CPFN.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item