AI Paper Atlas

Research map / Point clouds / Point cloud classification

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

Haowen Deng, Tolga Birdal, Slobodan Ilic

ECCV 2018 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 415 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
use 5K points per local patch instead of 2K (ablation)PPF-FoldNet · 3DMatch (standard)recall: 0.6804 -> 0.7182Improved
use 5K points per local patch instead of 2K (ablation)PPF-FoldNet · Rotated 3DMatchrecall: 0.6865 -> 0.7311Improved
replace PPFNet with PPF-FoldNet (unsupervised, PPF only)PPFNet · 3DMatch (standard)recall: 62.32% -> 68.04%Improved
replace FPFH with PPF-FoldNet to compress PPFsFPFH · 3DMatch (standard)recall: 0.3589 -> 0.6804Improved
use PPF-FoldNet instead of PPFNet under random rotationsPPFNet · Rotated 3DMatchrecall: 0.0026 -> 0.6865Improved
use PPF-FoldNet instead of CGF under random rotationsCGF · Rotated 3DMatchrecall: 0.4987 -> 0.6865Improved
use Bobkov1 PPF (with occupancy ratio) instead of the proposed PPF (ablation)PPF-FoldNet · Rotated 3DMatch subsetrecall: 0.463 -> 0.483No clear effect
use PPFH (FPFH-style PPF) instead of the proposed PPF (ablation)PPF-FoldNet · Rotated 3DMatch subsetrecall: 0.463 -> 0.436No clear effect
use PPF-FoldNet instead of FPFH for feature computationFPFH · 3DMatch fragmenttime (s): 31.678 -> 3.969Improved
decrease fragment points from 100% to 6.25% (ablation)PPF-FoldNet · 3DMatch sparsity testrecall: greater than 50%No clear effect
decrease fragment points to 6.25% for PPFNet (ablation)PPFNet · 3DMatch sparsity testrecall: around 12%Hurt
compare against PPFNet on standard scenes KitchenPPF-FoldNet (2K) · 3DMatch Kitchenrecall: 0.8972 -> 0.7352Hurt

Later papers that compared with this method

2 later accepted papers report PPF-FoldNet-5K as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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