AI Paper Atlas

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

CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception

Youngseok Kim, Juyeb Shin, Sanmin Kim, In-Jae Lee, Jun Won Choi, Dongsuk Kum

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion detection · 176 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 radar-assisted view transformation (depth plus radar occupancy) over depth-only (ablation)CRN camera stream · nuScenes valNDS: 43.9 -> 52.1Improved
replace depth distribution with raw radar occupancy for view transformation (ablation)CRN camera stream · nuScenes valNDS: 43.9 -> 33.6Hurt
use multi-modal deformable cross attention aggregation (MFA) instead of single-conv BEVFusion (ablation)CRN · nuScenes valNDS: 51.9 -> 53.4Improved
add two more fusion conv layers to BEVFusion (ablation)BEVFusion · nuScenes valNDS: 51.9 -> 51.9No clear effect
add RVT on top of MFA (ablation)CRN · nuScenes valNDS: 53.4 -> 53.9Improved
add sparse aggregation (top-k queries) (ablation)CRN long-range · nuScenes val 102.4m Car mAPCar mAP: mAP 56.9 -> 54.0, FPS 11.5 -> 14.0Mixed
keep only 1024 top-k queries instead of 4096 (ablation)CRN sparse aggregation · nuScenes val 100m CarAP: 54.0 -> 49.8Hurt
increase temporal BEV frames from 1 to 4 (ablation)CRN · nuScenes valNDS: 50.3 -> 56.0Improved
increase temporal frames from 4 to 5 (ablation)CRN · nuScenes valNDS: 56.0 -> 56.4No clear effect
fuse radar with camera using CRN under complete radar lossCRN vs BEVFusion · nuScenes val, robustness, no radarCar mAP: 34.4 -> 43.8Improved
add radar fusion to camera-only detectorBEVDepth · nuScenes val, nightmAP: 16.8 -> 30.4Improved

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