AI Paper Atlas

Research map / Point clouds / Segmentation and detection

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Danila Rukhovich, Anna Vorontsova, Anton Konushin

ECCV 2022 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 150 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 Mobius OBB parametrization instead of naive (ablation)VoteNet (IoU loss) · SUN RGB-DmAP@0.5: 38.4 -> 40.4Improved
use Mobius OBB parametrization instead of sin-cos (ablation)VoteNet (IoU loss) · SUN RGB-DmAP@0.5: 37.1 -> 40.4Improved
use Mobius OBB parametrization instead of naive (ablation)ImVoteNet (IoU loss) · SUN RGB-DmAP@0.5: 39.1 -> 40.8Improved
use Mobius OBB parametrization instead of naive (ablation)ImVoxelNet · SUN RGB-DmAP@0.5: 13.8 -> 14.6Improved
use Mobius OBB parametrization instead of naive (ablation)FCAF3D · SUN RGB-DmAP@0.5: 46.8 -> 48.9Improved
add anchors to GSDN (versus anchor-free GSDN) (ablation)GSDN · ScanNet V2mAP@0.5: 22.7 -> 34.8Improved
replace GSDN with anchor-free FCAF3D at same voxel size and strideGSDN · ScanNet V2mAP@0.5: 34.8 -> 46.2Improved
reduce voxel size from 0.03 to 0.01 m (ablation)FCAF3D · ScanNet V2mAP@0.5: 42.6 -> 57.3Improved
increase input points from 20k to 100k (ablation)FCAF3D · ScanNet V2mAP@0.5: 52.8 -> 57.3Improved
add centerness (ablation)FCAF3D · ScanNet V2mAP@0.5: 56.1 -> 57.3Improved
add centerness (ablation)FCAF3D · S3DISmAP@0.25: 67.9 -> 66.7Hurt
use 18 center-sampling locations instead of 9 (ablation)FCAF3D · ScanNet V2mAP@0.5: 55.7 -> 57.3Improved

Later papers that compared with this method

6 later accepted papers report FCAF3D as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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