AI Paper Atlas

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

MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps

Pengxiang Wu, Siheng Chen, Dimitris N. Metaxas

CVPR 2020 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 9 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
Use MotionNet instead of LSTM-Encoder-DecodernuScenes environmental state prediction · nuScenes testmean displacement error, speed > 5m/s: 1.5885 -> 1.0744Improved
Use MotionNet instead of LSTM-Encoder-DecodernuScenes environmental state prediction · nuScenes testinference time: 0.042s -> 0.019sImproved
Add spatial consistency loss L_s (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2488Improved
Add foreground temporal consistency loss L_ft (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2515Improved
Add background temporal consistency loss L_bt (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2530Improved
Add all three consistency losses (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2467Improved
Use MGDA for multi-task optimization (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2366Improved
Use MGDA alongside all consistency losses (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.2292Improved
Increase input history from 2 to 5 frames (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2921 -> 0.2565Improved
Remove ego-motion synchronization (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.4245Hurt
Replace ground-truth sweep synchronization with ICP (ablation)MotionNet · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2565 -> 0.4073Hurt
Use middle temporal fusion rather than early fusion (ablation)MotionNet with STC blocks · nuScenes testmean displacement error, speed ≤ 5m/s: 0.2596 -> 0.2565Improved

Later papers that compared with this method

1 later accepted paper reports MotionNet as a baseline in their results tables; 0 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