AI Paper Atlas

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

SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 172 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
use self-attention instead of MLP for sparse candidate fusion (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 64.5 -> 66.4Improved
use self-attention instead of cross-attention fusion (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 65.8 -> 66.4Improved
use self-attention instead of optimal transport fusion (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 65.6 -> 66.4Improved
add semantic transfer from camera to LiDAR (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 64.2 -> 66.4Improved
add geometric transfer from LiDAR to camera (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 65.7 -> 66.4Improved
add view transformation of camera candidates into LiDAR space (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 65.6 -> 66.4Improved
use parallel modality-specific detectors instead of sequential (ablation)SparseFusion · nuScenes val (1/5 train)mAP: 64.2 -> 66.4Improved
swap ResNet-50 for stronger Swin-T image backboneSparseFusion · nuScenes valNDS: 72.8 -> 73.1Improved
add semantic transfer to the LiDAR branchTransFusion-L · nuScenes valmAP: 65.1 -> 68.4Improved
add camera view transformation module to camera branchcamera branch · nuScenes valmAP: 40.6 -> 41.5Improved

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