AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion

Yang Liu, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

NeurIPS 2023 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 13 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
fuse raw radar range-time data with camera via polar-aligned attention instead of FFTRadNet3D RD-onlyEchoFusion · RADIal refined 3D boxesBEV AP@0.7 overall: 57.26 -> 84.92Improved
add camera image to radar-only range-time input (ablation)EchoFusion RT · RADIal refined 3D boxesBEV AP@0.7 overall: 48.26 -> 84.92Improved
use raw radar (RT) instead of CFAR radar point cloud when fused with camera (ablation)EchoFusion · RADIal refined 3D boxesBEV AP@0.7 overall: 82.35 -> 84.92Improved
use range-azimuth map instead of range-time data (ablation)EchoFusion C+radar · RADIal refined 3D boxesBEV AP@0.7 overall: 84.92 -> 84.77No clear effect
decompose complex radar input into magnitude and phase instead of IQ (ablation)EchoFusion · RADIal refined 3D boxesBEV AP@0.7 overall: 82.64 -> 84.92Improved
use pre-trained image backbone (ablation)EchoFusion · RADIal refined 3D boxesBEV AP@0.7 overall: 74.34 -> 84.92Improved
replace polar with sphere BEV coordinate system (ablation)EchoFusion · RADIal refined 3D boxesBEV AP@0.7 overall: 84.92 -> 85.02No clear effect
use range-azimuth map + camera instead of radar point cloud + camera (ablation)EchoFusion · KRadar-20 train splitBEV AP@0.7: 26.39 -> 29.65Improved
use EchoFusion with image and RA map instead of RTNH point cloudKRadar-20 trainval · KRadar-20 testBEV AP@0.7: 10.47 -> 33.07Improved
fuse radar RT with camera for 3D AP versus LiDAREchoFusion · RADIal 3D AP@0.53D AP@0.5 overall: 62.69 -> 39.81Hurt

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