AI Paper Atlas

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

RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weather

Heejun Park, Jaeseok Jeong, KUK-JIN YOON

ECCV 2026 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion detection · 1 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 camera branch with reliability supervision (RAF)L4DR · K-Radar TotalAP_BEV: 77.5 -> 82.0Improved
add camera branch with reliability supervision (RAF)3D-LRF · K-Radar TotalAP_BEV / AP_3D: 64.5 -> 71.0 / 35.8 -> 43.2Improved
add unsupervised confidence gating (detection loss only) (ablation)L4DR with pretrained frozen backbone · K-Radar TotalAP_BEV: 78.6 -> 76.4Hurt
add unsupervised confidence gating (detection loss only) (ablation)3D-LRF with frozen backbone · K-Radar TotalAP_3D: 39.1 -> 33.1Hurt
add weakly-supervised reliability estimation (sim + rel losses) (ablation)L4DR · K-Radar TotalAP_BEV: 76.4 -> 80.2Improved
add Calibration-Aware Local Matching (CALM) (ablation)L4DR · K-Radar TotalAP_BEV / AP_3D: 80.2 -> 82.0 / 55.4 -> 57.4Improved
add CALM (ablation)3D-LRF · K-Radar TotalAP_BEV / AP_3D: 70.5 -> 71.0 / 41.9 -> 43.2Improved
use pretrained frozen LiDAR-RADAR backbone instead of joint training (ablation)L4DR / 3D-LRF · K-Radar TotalAP_BEV: 77.8 -> 78.6 (L4DR); 65.7 -> 68.3 (3D-LRF)Improved
enlarge CALM window from 5 to 7 (ablation)RAF · K-Radar TotalAP_3D: 57.4 -> 55.4 (L4DR); 43.2 -> 39.8 (3D-LRF)Hurt
use hard gating alpha=0 instead of alpha=0.2 (ablation)RAF · K-Radar TotalAP_3D: 3D-LRF 43.2 -> 45.0; L4DR 57.4 -> 58.5Mixed
replace CNN reliability estimator with ViT (ablation)RAF · K-Radar TotalAP_3D: 57.4 -> 56.4 (L4DR); 43.2 -> 40.2 (3D-LRF)Hurt
naive camera fusion in adverse weather (Joint/Frozen) vs LiDAR-RADAR baselineL4DR / 3D-LRF · K-Radar Noisy splitAP_BEV: L4DR 59.0 -> 55.6; 3D-LRF 38.8 -> 25.4 (Joint)Hurt

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