AI Paper Atlas

Research map / Point clouds / Point cloud classification

Fully Convolutional Geometric Features

Christopher Choy, Jaesik Park, Vladlen Koltun

ICCV 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 852 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 hardest-negative mining in contrastive loss instead of random contrastive (ablation)FCGF contrastive loss · 3DMatch 5cmfeature-match recall: 0.7309 -> 0.9344Improved
use hardest-contrastive loss instead of normalized contrastive loss (ablation)FCGF · 3DMatch 5cmfeature-match recall: 0.8493 -> 0.9344Improved
use hardest-contrastive instead of best hardest-triplet mixture (ablation)FCGF · 3DMatch 5cmfeature-match recall: 0.9087 -> 0.9344Improved
add hardest negatives to random triplets (128 HN with 2048 RT) (ablation)triplet loss · 3DMatch 5cmfeature-match recall: 0.7903 -> 0.9087Improved
increase number of hardest negatives to 1024 with 512 random triplets (ablation)hardest-triplet loss · 3DMatch 5cmfeature-match recall: COLLAPSEHurt
normalize features in contrastive loss (ablation)contrastive loss · 3DMatch 5cmfeature-match recall: 0.7309 -> 0.8493Improved
normalize features in triplet loss (ablation)triplet loss · 3DMatch 5cmfeature-match recall: 0.7903 -> 0.6935Hurt
increase feature dimension from 16 to 64 (ablation)FCGF hardest-contrastive · 3DMatch 5cmfeature-match recall: 0.9011 -> 0.9343Improved
increase feature dimension from 32 to 48 (ablation)FCGF hardest-contrastive · 3DMatch 5cmfeature-match recall: 0.9242 -> 0.9235No clear effect
use 64-dim features at 2.5cm voxel (ablation)FCGF hardest-contrastive · 3DMatch 2.5cmfeature-match recall: OOMHurt
raise negative margin from 0.5 to 2 at positive margin 0.1 (ablation)FCGF hardest-contrastive · 3DMatch 5cmfeature-match recall: 0.8832 -> 0.9344Improved
increase positive margin from 0.1 to 0.4 at negative margin 1 (ablation)FCGF hardest-contrastive · 3DMatch 5cmfeature-match recall: 0.9249 -> 0.9013Hurt

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