AI Paper Atlas

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

Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation

Duy Tho Le, Hengcan Shi, Jianfei Cai, Hamid Rezatofighi

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 24 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 cMini-BiFPN fusion architecture (ablation)BEVFusion baseline · nuScenes val BEV segmentationmIoU: 62.7 -> 66.5Improved
add cMini-BiFPN fusion architecture (ablation)BEVFusion baseline · nuScenes val 3D detectionNDS: 71.4 -> 71.8Improved
add GSM module with PSDT (4-step sampling) (ablation)cMini-BiFPN · nuScenes val BEV segmentationmIoU: 66.5 -> 68.82Improved
increase diffusion sampling from 4 to 8 steps (ablation)DifFUSER · nuScenes val BEV segmentationmIoU: 68.82 -> 70.04Improved
add Shift to Scale in GSM (ablation)GSM block · nuScenes val BEV segmentation (6-epoch)mIoU: 59.92 -> 60.73Improved
add Gate to Scale and Shift in GSM (ablation)GSM block · nuScenes val BEV segmentation (6-epoch)mIoU: 60.73 -> 62.17Improved
swap DDIM for DPM-Solver++ or DEIS (ablation)DifFUSER sampler · nuScenes val BEV segmentationmIoU: 70.04 -> 70.02 / 69.95No clear effect
joint multi-task training instead of single-task (ablation)DifFUSER · nuScenes valNDS / mIoU: NDS 69.59 -> 68.23; mIoU 65.8 -> 61.36Hurt
replace BEVFusion with DifFUSER for fusionBEVFusion · nuScenes val BEV segmentationmIoU: 62.7 -> 70.04Improved
replace BEVFusion with DifFUSER for fusionBEVFusion · nuScenes test 3D detectionNDS: 72.9 -> 73.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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