AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Deep Hough Voting for 3D Object Detection in Point Clouds

Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas

ICCV 2019 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 1,291 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 voting (vote then cluster) instead of direct box proposal from seeds (ablation)VoteNet · SUN RGB-D valmAP@0.25: 53.0 -> 57.7Improved
add voting instead of direct box proposal from seeds (ablation)VoteNet · ScanNetV2 valmAP@0.25: 45.4 -> 58.6Improved
use learned PointNet vote aggregation with max pooling instead of manual pooling (max, avg, RBF) (ablation)VoteNet · SUN RGB-D valmAP@0.25Improved
increase aggregation radius beyond about 0.2 (ablation)VoteNet · SUN RGB-D valmAP@0.25Hurt
vote from deeper seed features (SA2 to FP2) (ablation)VoteNet · SUN RGB-D valmAP@0.25: 51.2 -> 57.7Improved
extend seed context to FP3 beyond FP2 (ablation)VoteNet · SUN RGB-D valmAP@0.25: 57.7 -> 57.1No clear effect
generate 3 votes per seed instead of 1 (ablation)VoteNet · SUN RGB-D valmAP@0.25: 57.7 -> 55.8Hurt
add random number to break symmetry with 3 votes per seed (ablation)VoteNet · SUN RGB-D valmAP@0.25: 55.8 -> 55.8No clear effect
change proposal sampling from seed FPS to random or vote FPS (ablation)VoteNet · SUN RGB-D valmAP@0.25: 57.7 -> 57.5No clear effect
add the height feature (ablation)VoteNet · SUN RGB-D valmAP@0.25: 57.0 -> 57.7Improved
add the height feature (ablation)VoteNet · ScanNetV2 valmAP@0.25: 58.1 -> 58.6Improved
use point-based voting with geometry only instead of 3D CNN 3D-SIS (geo only)3D-SIS · ScanNetV2 valmAP@0.25: 25.4 -> 58.6Improved

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