AI Paper Atlas

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

DeGuNet: Depth-Guided Ultra-Compact Backbones for Efficient LiDAR-Camera 3D Detection

haifa zhang, Yijing Wang, Peixi Peng, Zhiqiang Zuo

ECCV 2026 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 0 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 2D-pretrained backbone with DeGuNetBEVFusion'23 · nuScenes valmAP: 68.50 -> 69.40Improved
replace backbone with DeGuNetEA-LSS · nuScenes valmAP: 70.9 -> 71.1Improved
replace backbone with DeGuNetGraphBEV · nuScenes valNDS: 72.9 -> 72.9No clear effect
replace backbone with DeGuNetIS-Fusion · nuScenes valmAP: 71.0 -> 71.3Improved
replace backbone with DeGuNetBEVFusion · nuScenes val (efficiency, A100)GPU memory: 20.46GB -> 6.86GBImproved
replace backbone with DeGuNetBEVFusion · nuScenes val (efficiency, A100)FPS: 4.4 -> 5.1Improved
pretrain generic lightweight backbones (ResNet, MobileViT) on depth completion instead of using sparsity-aware DeGuNet (ablation)lightweight backbones · Depth pretraining on KITTI, downstream nuScenes 3D detmAP: 62.11 / 62.09 vs 69.40 (DeGuNet)Hurt
scale up to Swin-T for depth pretraining instead of sparsity-aware design (ablation)depth-pretrained backbone · Depth pretraining on KITTI, downstream nuScenes 3D detmAP: 64.01 vs 69.40Hurt
use DeGuNet backbone instead of auxiliary BEVDepth supervision (ablation)BEVFusion · nuScenes val (auxiliary depth comparison)mAP: 64.8 -> 70.3Improved
add MPIR blocks (ablation)LiDAR baseline (BEVFusion'23) · nuScenes val (BEVFusion'23 ablation)mAP: 64.66 -> 66.14Improved
add progressive Guide modules (ablation)MPIR variant · nuScenes val (BEVFusion'23 ablation)mAP: 66.14 -> 67.24Improved
add MMViT mask-aware attention (ablation)MPIR+Guide variant · nuScenes val (BEVFusion'23 ablation)mAP: 67.24 -> 68.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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