AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

Zaiwei Zhang, Bo Sun, Haitao Yang, Qixing Huang

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 203 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 refinement of object center (ablation)H3DNet · ScanNet V2 valmAP@0.5: 46.3 -> 48.1Improved
add refinement of object size (ablation)H3DNet · ScanNet V2 valmAP@0.5: 44.2 -> 48.1Improved
add refinement of semantic label (ablation)H3DNet · ScanNet V2 valmAP@0.5: 47.3 -> 48.1Improved
add refinement of object existence score (ablation)H3DNet · ScanNet V2 valmAP@0.5: 45.1 -> 48.1Improved
add refinement of heading angle (ablation)H3DNet · SUN RGB-D V1 valmAP@0.25: 58.6 -> 60.1Improved
add refinement of heading angle (ablation)H3DNet · SUN RGB-D V1 valmAP@0.5: 36.6 -> 39.0Improved
add refinement of object center (ablation)H3DNet · ScanNet V2 valmAP@0.25: 66.9 -> 67.2Improved
add primitive matching and proposal refinement (vs classifying initial proposals only) (ablation)H3DNet · ScanNet V2 valmAP@0.5: 14.6% drop on mAP 0.5 withoutImproved
increase descriptor computation towers from 1 to 4 (ablation)H3DNet · ScanNet V2 valmAP@0.25: 64.4 -> 67.2Improved
increase descriptor computation towers from 1 to 4 (ablation)H3DNet · ScanNet V2 valmAP@0.5: 43.4 -> 48.3Improved
give VoteNet four descriptor towers (ablation)VoteNet · ScanNet V2 valmAP@0.5: 33.5 -> 37.12No clear effect
give VoteNet four descriptor towers (ablation)VoteNet · SUN RGB-D V1 valmAP@0.25: 57.7 -> 57.5No clear effect

Later papers that compared with this method

6 later accepted papers report H3DNet as a baseline in their results tables; 4 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