AI Paper Atlas

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

3D Small Object Detection with Dynamic Spatial Pruning

Zhihao Sun, Ziwei Wang, Hongmin Liu, Jie Zhou, Jiwen Lu, Xiuwei Xu

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 6 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
double the spatial resolution of TR3DTR3D · 3D small object detectionmAP_S: 52.7% -> 62.8%Improved
double the spatial resolution of TR3DTR3D · ScanNet-md40memory: 1250 -> 4450Hurt
add dynamic spatial pruning (tau=0.3) to the higher-resolution TR3DTR3D-higher · ScanNet-md40speed (FPS): 5.2 -> 12.5Improved
add dynamic spatial pruning (tau=0.3)TR3D-higher · ScanNet-md40memory: 4450 -> 700Improved
increase pruning threshold from 0 to 0.3 (ablation)DSPDet3D · ScanNet-md40mAP_S@0.25: 44.79 -> 43.77Hurt
use DSPDet3D (tau=0) instead of TR3D-higherTR3D-higher · ScanNet-md40mAP_S@0.25: 41.70 -> 44.79Improved
use partial addition instead of removing it (ablation)DSP module · ScanNet-md40 (10 FPS)mAP: 55.3 -> 65.1Improved
use partial addition instead of union addition (ablation)DSP module · ScanNet-md40 (10 FPS)mAP: 57.9 -> 65.1Improved
use affecting-field-shaped keeping mask instead of spherical mask (ablation)DSP module · ScanNet-md40 (10 FPS)mAP: 63.0 -> 65.1Improved
sample positives inside P-cube instead of inside bounding box (ablation)DSP module · ScanNet-md40 (10 FPS)mAP: 62.4 -> 65.1Improved
add training-time weak pruning (ablation)DSP module · ScanNet-md40trainabilityImproved
set r=7 (with P=7) instead of smaller r (ablation)DSPDet3D · ScanNet-md40mAPImproved

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