AI Paper Atlas

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

LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection

Yihan Zeng, Da Zhang, Chunwei Wang, Zhenwei Miao, Ting Liu, Xin Zhan, Dayang Hao, Chao Ma

CVPR 2022 · Detection and segmentation › 3D detection and driving · approach: Camera-radar fusion detection · 37 citations (OpenAlex)

Check 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
Fuse LiDAR, camera images, and sequential information with sensor-time attention rather than use LiDAR alone (ablation)PointPillars · nuScenes validation subset (1/8 training)mAP: 24.83 -> 47.04Improved
Use self-attention rather than concatenation to fuse LiDAR and images (ablation)PointPillars · nuScenes validation subset (1/8 training), LiDAR + imagesmAP: 41.59 -> 43.22Improved
Use self-attention rather than concatenation to fuse LiDAR and sequential input (ablation)PointPillars · nuScenes validation subset (1/8 training), LiDAR + timemAP: 26.74 -> 27.75Improved
Increase sequence length from T=2 to T=5 with LIFT attention (ablation)LIFT · nuScenes validation subset (1/8 training)mAP: T=2: 27.75; T=5: 30.97Improved
Replace attention temporal fusion with point concatenation (ablation)LIFT · nuScenes validation subset (1/8 training), T=2 (+Img)mAP: 47.04 -> 43.74Hurt
Add cross-sensor and cross-time-consistent augmentation (ablation)LIFT · nuScenes validation subset (1/8 training), sequential point-cloud and image inputmAP: 47.04 -> 51.78Improved
Add point-wise attention within pillars (ablation)LIFT · nuScenes validation subset (1/8 training)mAP: 49.76 -> 50.25Improved
Add 4D relative positional encoding (ablation)LIFT · nuScenes validation subset (1/8 training)mAP: 50.25 -> 50.50Improved
Add pyramid context (ablation)LIFT · nuScenes validation subset (1/8 training)mAP: 50.50 -> 51.30Improved
Add sparse window partition (ablation)LIFT · nuScenes validation subset (1/8 training)mAP: 51.30 -> 51.78Improved
Increase image resolution from 448 × 800 to 896 × 1600 (ablation)LIFT · nuScenes validationmAP: 51.78 -> 51.83No clear effect
Reduce image resolution from 448 × 800 to 224 × 400 (ablation)LIFT · nuScenes validationmAP: 51.78 -> 44.20Hurt

Later papers that compared with this method

5 later accepted papers report LiFT as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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