AI Paper Atlas

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

Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection

Junjie Huang, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 48 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
replace BEVFusion-style pipeline with DAL pipeline (no image features in regression) plus auxiliary head, under simple training (ablation)LiDAR-camera fusion · nuScenes valNDS: 69.00 -> 69.52 vs LiDAR-onlyImproved
train BEVFusion pipeline with simple ImageNet-only training (ablation)BEVFusion · nuScenes valNDS: 69.00 -> 68.71No clear effect
add large-range image resize augmentation (ablation)DAL · nuScenes valmAP / NDS: +3.91 mAP and +1.35 NDSImproved
add velocity augmentation of static objects (ablation)DAL · nuScenes valmAP / NDS: +0.47 mAP and +1.07 NDS; mAVE 25.80 -> 19.31Improved
add auxiliary classification head to BEVFusion-like pipeline (ablation)BEVFusion · nuScenes valNDS: 68.71 -> 68.99No clear effect
large resize augmentation on BEVFusion-like pipeline instead of DAL pipeline (ablation)BEVFusion · nuScenes valNDS: 68.99 -> 70.97Improved
DAL pipeline vs BEVFusion pipeline with velocity augmentation (ablation)DAL · nuScenes valNDS: 71.67 -> 71.94Improved
increase image resolution or image backbone capacity beyond R50 256x704 (ablation)DAL image branch · nuScenes valNDS: 71.94 -> 72.13 at 384x1056; 71.94 -> 71.62 with R101No clear effect
increase LiDAR voxel resolution from 0.100 to 0.075 (ablation)DAL LiDAR branch · nuScenes valNDS: 71.94 -> 72.64Improved
use DAL-Base instead of CMT-R50 at similar speedDAL-Base · nuScenes valmAP / NDS: +2.1 mAP and +2.6 NDSImproved
handle objects beyond LiDAR range with a separate fused-feature regression FFN (ablation)DAL · nuScenesaccuracyNo clear effect

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