AI Paper Atlas

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

Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View

Jiayu Yang, Enze Xie, Miaomiao Liu, Jose M. Alvarez

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 10 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 parametric depth lifting together with occupancy-aware aggregation (ablation)BEV feature transformation · nuScenes val (ResNet-50)mAP: 0.408 -> 0.424 (uniform + PointPillars to full)Improved
replace PointPillars aggregation with occupancy-aware aggregation (parametric lifting) (ablation)parametric depth lifting · nuScenes val (ResNet-50)mAP: 0.410 -> 0.424Improved
replace PointPillars aggregation with occupancy-aware aggregation (non-parametric or uniform lifting) (ablation)LSS or uniform lifting · nuScenes val (ResNet-50)mAP: 0.409 -> 0.414 (non-parametric); 0.408 -> 0.413 (uniform)Improved
replace parametric depth lifting with parametric lifting only with PointPillars aggregation (ablation)BEV feature lifting · nuScenes val (ResNet-50)mAP: 0.408 -> 0.410No clear effect
remove LiDAR depth supervision from parametric depth (ablation)Ours · nuScenes val BEV segmentationRoad IoU: 78.7 -> 77.9Hurt
use parametric depth method versus M2BEV on visible regionsBEV segmentation · nuScenes val visible regionRoad IoU: 82.9 -> 84.8Improved
use parametric depth method versus M2BEV on occluded regionsBEV segmentation · nuScenes val occluded regionLane IoU: 12.8 -> 12.4No clear effect
use parametric depth instead of M2BEV uniform depth in joint multi-task settingM2BEV · nuScenes val jointmAP / NDS / Road / Lane: mAP 0.408 -> 0.424; NDS 0.454 -> 0.467Improved
predict extra depth parameters (parametric depth) versus uniform depthBEV model · nuScenes efficiencymemory / FPS: memory 7718 -> 8902; FPS 1.2 -> 1.3Mixed

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