AI Paper Atlas

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

ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion

Qi Cai, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 72 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 all three object-centric features (BEV, voxel, image) instead of one (ablation)ObjectFusion · nuScenes valmAP (%): 69.3 -> 69.8Improved
add modality-specific context encoder (MSCE) (ablation)ObjectFusion · nuScenes valmAP (%): 69.3 -> 69.8Improved
add MSCE (NDS) (ablation)ObjectFusion · nuScenes valNDS (%): 71.5 -> 72.3Improved
replace BEV-based fusion with object-centric fusionBEVFusion · nuScenes valmAP (%): 68.5 -> 69.8Improved
object-centric fusion instead of BEV fusion in night scenesBEVFusion · nuScenes val, NightmAP (%): 42.8 -> 46.0Improved
add translation offsets to camera-LiDAR calibration (with RoI enlarging) (ablation)ObjectFusion · nuScenes valmAP (%): 69.8 -> 69.3 at 1.0m offsetNo clear effect
object-centric fusion on Waymo versus TransFusionTransFusion · Waymo valL2 mAPH (%): 65.5 -> 66.3Improved
extract and fuse object-centric featuresBEVFusion · nuScenes valinference time (ms): 257 -> 274Hurt
object-centric fusion instead of BEV fusion for trackingBEVFusion · nuScenes tracking valAMOTA (%): 72.8 -> 74.2Improved

Later papers that compared with this method

1 later accepted paper reports ObjectFusion as a baseline in their results tables; 1 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