AI Paper Atlas

Research map / Point clouds / Segmentation and detection

EPNet++: Cascade Bi-Directional Fusion for Multi-Modal 3D Object Detection

Zhe Liu, Tengteng Huang, Bingling Li, Xiwu Chen, Xi Wang, Xiang Bai

TPAMI 2022 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 171 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 CB-Fusion only (no MC loss) (ablation)EPNet LiDAR-only · KITTI val Cars Moderate (16-beam)AP: 63.30 -> 68.83Improved
add LI-Fusion only (ablation)EPNet LiDAR-only · KITTI val Cars Moderate (16-beam)AP: 63.30 -> 67.72Improved
add MC loss only (ablation)EPNet LiDAR-only · KITTI val Cars Moderate (16-beam)AP: 63.30 -> 63.69Improved
add MC loss on top of CB-Fusion (ablation)EPNet++ · KITTI val Cars Moderate (16-beam)AP: 68.83 -> 69.12Improved
add attention to CB-Fusion on 16-beam Pedestrians (ablation)EPNet++ · KITTI val 16-beam PedestriansAP: 3.45%Improved
add attention to LI-Fusion on 16-beam Pedestrians (ablation)EPNet · KITTI val 16-beam PedestriansAP: 0.90%Improved
use cascade CB-Fusion instead of parallel bi-directional fusion (ablation)EPNet++ · KITTI val (64-beam)AP: 73.25 -> 74.04Improved
use CB-Fusion instead of reversed order (ablation)EPNet++ · KITTI val (64-beam)AP: 73.39 -> 74.04Improved
add CB-Fusion to LiDAR-only EPNet vs PointPainting fusion (ablation)EPNet baseline · KITTI val (64-beam)AP: 72.14 -> 73.11Improved
use transformer-based CB-Fusion instead of attention-gated CB-Fusion (ablation)EPNet++ · KITTI val (64-beam)AP: 73.11 -> 72.50Hurt
add LI-Fusion without I2P attention gate (ablation)LiDAR-only baseline · KITTI val (noisy-data analysis)AP: 67.89 -> 67.77Hurt
add I2P attention gate to LI-Fusion (ablation)LI-Fusion · KITTI val (noisy-data analysis)AP: 67.77 -> 69.63Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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