AI Paper Atlas

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

Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection

Zhili Chen, Shuangjie Xu, Maosheng Ye, Zian Qian, Xiaoyi Zou, Dit-Yan Yeung, Qifeng Chen

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 4 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 vector query representation to BEVFormer-SBEVFormer-S · nuScenes valNDS: 47.9 -> 51.0Improved
add vector representation to DFA3D-SDFA3D-S · nuScenes valNDS: 50.1 -> 51.4Improved
add vector representation to BEVFormer-BBEVFormer-B · nuScenes valNDS: 51.7 -> 53.2Improved
use vector queries with coarser BEV grid instead of larger BEV gridBEVFormer · nuScenes valMemory: 5.58 -> 4.83Improved
increase BEV resolution in plain BEVFormer (ablation)BEVFormer · nuScenes valNDS: 51.7 -> 51.9No clear effect
increase vector dimension from 200 to 450 at fixed 200x200 BEV (ablation)VectorFormer · nuScenes valNDS: 52.8 -> 53.2Improved
add heatmap supervision for BEV features (ablation)VectorFormer-S · nuScenes val (12 epochs)NDS: 48.4 -> 48.9Improved
add vector representation for spatial modeling (ablation)VectorFormer-S · nuScenes val (12 epochs)NDS: 48.9 -> 49.5Improved
add temporal modeling of vector queries (ablation)VectorFormer-S · nuScenes val (12 epochs)NDS: 49.5 -> 49.7Improved
combine x/y vectors by addition instead of multiplication (ablation)VectorFormer-S · nuScenes val (12 epochs)NDS: 49.4 -> 49.7Improved
increase top-k proposals from 2 to 4 (ablation)VectorFormer-S · nuScenes val (12 epochs)NDS: 49.5 -> 50.0Improved
add deformable offset prediction (ablation)VectorFormer-S · nuScenes val (12 epochs)mAP: 39.2 -> 39.8Improved

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