AI Paper Atlas

Research map / Point clouds / Segmentation and detection

MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection

Zitian Wang, Zehao Huang, Yulu Gao, Naiyan Wang, Si Liu

TPAMI 2025 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 43 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
raise image resolution from 704x256 to 1600x640 (ablation)MV2DFusion · nuScenes valNDS: 0.740 -> 0.745Improved
use ConvNext-L backbone instead of ResNet-50 (ablation)MV2DFusion · nuScenes valNDS: 0.747 -> 0.755Improved
swap 2D detector (YOLOX, Faster R-CNN, Cascade R-CNN) (ablation)MV2DFusion · nuScenes valNDS: 0.745 -> 0.747No clear effect
remove camera input at test timeMV2DFusion trained with both · nuScenes valNDS: 0.747 -> 0.469Hurt
add mixed-modality training (ablation)MV2DFusion · nuScenes val, camera onlyNDS: 0.469 -> 0.523Improved
add mixed-modality training (ablation)MV2DFusion · nuScenes val, camera and LiDARNDS: 0.747 -> 0.748Improved
use distribution instead of point image queries (ablation)MV2DFusion · nuScenes valNDS: 0.743 -> 0.747Improved
use distribution instead of point image queries (ablation)MV2DFusion · AV2 valCDS: 0.373 -> 0.395Improved
add image queries to LiDAR-only queries (ablation)MV2DFusion · nuScenes valNDS: 0.737 -> 0.747Improved
add LiDAR queries to image-only queries (ablation)MV2DFusion · nuScenes valNDS: 0.733 -> 0.747Improved
add cross-attention to decoder (ablation)MV2DFusion · nuScenes valmAP: 0.715 -> 0.728Improved
increase decoder layers from 3 to 6 (ablation)MV2DFusion · nuScenes valNDS: 0.746 -> 0.747No clear effect

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