AI Paper Atlas

Research map / Point clouds / Segmentation and detection

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

Tengteng Huang, Zhe Liu, Xiwu Chen, Xiang Bai

ECCV 2020 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 537 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 LI-Fusion modules (point-wise image feature fusion) (ablation)EPNet two-stream RPN · KITTI val 3D3D mAP: 79.94 -> 81.67Improved
add consistency enforcing (CE) loss (ablation)EPNet · KITTI val 3D3D mAP: 79.94 -> 83.87Improved
add LI-Fusion on top of CE loss (ablation)EPNet · KITTI val 3D3D mAP: 83.87 -> 85.00Improved
replace CE loss with IoU loss (ablation)EPNet · KITTI val 3D3D mAP: CE loss gives +1.28% 3D mAP over IoU lossImproved
fuse RGB by simple concatenation with point coordinates instead of feature fusion (ablation)geometric stream · KITTI val 3D3D mAP: 79.94 -> 79.66Hurt
single-scale fusion (last FP layer only) instead of baseline without fusion (ablation)EPNet · KITTI val 3D3D mAP: 79.94 -> 80.36Improved
use multi-scale LI-Fusion instead of single-scale fusion (ablation)EPNet · KITTI val 3D3D mAP: 80.36 -> 81.67Improved
simple RGB concatenation under altered illumination (ablation)LiDAR-only model · KITTI val 3D, altered illumination3D mAP: 83.87 -> 82.79Hurt
LI-Fusion without weight map under altered illumination (ablation)LiDAR-only model · KITTI val 3D, altered illumination3D mAP: 83.87 -> 83.18Hurt
add LiDAR-guided weight map w to LI-Fusion (ablation)LI-Fusion · KITTI val 3D, altered illumination3D mAP: 83.18 -> 84.52Improved
add CE loss instead of IoU loss: kept positive candidate box ratio (ablation)EPNet · KITTI valratio of kept positive candidate boxesImproved

Later papers that compared with this method

1 later accepted paper reports EPNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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