AI Paper Atlas

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

Forecasting From LiDAR via Future Object Detection

Neehar Peri, Jonathon Luiten, Mengtian Li, Aljoša Ošep, Laura Leal-Taixé, Deva Ramanan

CVPR 2022 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 34 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
predict future detections and backcast them to current detections instead of forecasting forward from current detectionsCenterPoint-based end-to-end car forecasting · nuScenes val cars, K=1mAP_f: 31.5 -> 33.5Improved
predict multiple future hypotheses and evaluate the top 5FutureDet · nuScenes val carsmAP_f: 33.5 -> 35.6Improved
use a PointPillars backbone instead of the default backbone (ablation)FutureDet · nuScenes val cars, K=1mAP_f: 33.5 -> 32.8Hurt
use a PointPillars backbone instead of the default backbone (ablation)FutureDet · nuScenes val cars, K=5mAP_f: 35.6 -> 36.1Improved
add road masks as an input channel (ablation)FutureDet · nuScenes val cars, K=1mAP_f: 33.5 -> 33.1Hurt
add road masks as an input channel (ablation)FutureDet · nuScenes val pedestrians, K=1mAP_f: 26.9 -> 26.5No clear effect
use a PointPillars backbone instead of the default backbone (ablation)FutureDet · nuScenes val pedestrians, K=1mAP_f: 26.9 -> 21.3Hurt
use a constant position forecast instead of a motion-aware forecastconstant-position baseline · nuScenes val carsADE@60: 0.38 (Constant Position); 0.74 (Fast and Furious*)Mixed
use a constant position forecast instead of forecasting movementconstant-position baseline · nuScenes val carsmAP_f: 22.1 -> 31.5Hurt
use trajectory-level copy-paste augmentation to oversample linear and nonlinear trajectoriesFutureDet training · nuScenes val carsAP_fImproved

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