AI Paper Atlas

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

CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection

Hanzhi Zhong, Zhiyu Xiang, Ruoyu Xu, Jingyun Fu, Peng Xu, Shaohong Wang, Zhihao Yang, Tianyu Pu, Eryun Liu

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion 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
add camera to radar-only input (ablation)CVFusion BEV baseline · VoD valmAP (%): 46.7 -> 57.1Improved
add radar guided iterative (RGIter) BEV fusion to simple concatenation (ablation)CVFusion stage1 · VoD valmAP (%): 57.1 -> 59.7Improved
add radar guidance (RG) to BEV concatenation (ablation)CVFusion stage1 · VoD valmAP (%): 57.1 -> 57.7Improved
add multi-scale fusion (ablation)CVFusion stage1 · VoD valmAP (%): 57.7 -> 58.8Improved
add iterative mechanism (ablation)CVFusion stage1 · VoD valmAP (%): 58.8 -> 59.7Improved
add RGIter to stage1: proposal recall (ablation)CVFusion stage1 · VoD valrecall (%): 72.0 -> 74.9Improved
add PGF with radar features only to stage1 (ablation)CVFusion · VoD valmAP (%): 59.7 -> 58.7Hurt
add KDE features to PGF (ablation)CVFusion PGF · VoD valmAP (%): 58.7 -> 59.2Improved
add CMDA image fusion to PGF (ablation)CVFusion PGF · VoD valmAP (%): 59.2 -> 61.7Improved
add first CMDA block (image FV) in GGF to PGF (ablation)CVFusion stage2 · VoD valmAP (%): 61.7 -> 62.8Improved
add second CMDA block (BEV) in GGF (ablation)CVFusion stage2 · VoD valmAP (%): 62.8 -> 64.4Improved
add self-attention over PGF and GGF features (ablation)CVFusion stage2 · VoD valmAP (%): 64.4 -> 65.41Improved

Later papers that compared with this method

2 later accepted papers report CVFusion as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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