AI Paper Atlas

Research map / Point clouds / Shape and surface completion

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

Eric-Tuan Lê, Minhyuk Sung, Duygu Ceylan, Radomir Mech, Tamy Boubekeur, Niloy J. Mitra

ICCV 2021 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add local cascaded SPFN (CPFN, eta=5%) on top of global SPFNSPFN · TraceParts high-resolution primitive fitting (128k points)segmentation mIoU (%): 66.29 -> 79.64Improved
add local cascadeSPFN · TraceParts high-resolution primitive fitting (128k points)primitive type accuracy (%): 89.50 -> 96.45Improved
increase patch scale threshold eta from 1% to 5%CPFN · TraceParts high-resolution primitive fitting (128k points)segmentation mIoU (%): 70.11 -> 79.64Improved
add local cascade for smallest primitives (<1% scale)SPFN · TraceParts high-resolution primitive fitting (128k points)per-scale mIoU: 44.25 -> 65.74Improved
add object-level global features l_o (ablation)CPFN local SPFN · TraceParts high-resolution primitive fitting (128k points) ablationsegmentation mIoU (%): 77.70 -> 78.30Improved
add patch features l_i^g from global SPFN (ablation)CPFN local SPFN · TraceParts high-resolution primitive fitting (128k points) ablationsegmentation mIoU (%): 77.70 -> 77.95Improved
add both l_o and l_i^g (ablation)CPFN local SPFN · TraceParts high-resolution primitive fitting (128k points) ablationprimitive axis difference (deg): 3.07 -> 1.44Improved
add global SPFN predictions in merging (ablation)CPFN · TraceParts high-resolution primitive fitting (128k points) ablationsegmentation mIoU (%): 74.13 -> 79.64Improved
add patch selection network (ablation)CPFN · TraceParts high-resolution primitive fitting (128k points) ablationsegmentation mIoU (%): 78.44 -> 79.64Improved
add patch selection network (ablation)CPFN · TraceParts high-resolution primitive fitting (128k points) ablationP coverage eps=0.01 (%): 74.42 -> 88.73Improved
use ground truth patch selection instead of learned one (ablation)CPFN · TraceParts high-resolution primitive fitting (128k points) ablationsegmentation mIoU (%): 79.64 -> 80.94No clear effect
use CPFN instead of SPFN at 16k points (ablation)SPFN · TraceParts (16k points)segmentation mIoU (%): 65.86 -> 74.77Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy