AI Paper Atlas

Research map / 3D vision / Human pose estimation

Robust 2D/3D Vehicle Parsing in Arbitrary Camera Views for CVIS

Hui Miao, Feixiang Lu, Zongdai Liu, Liangjun Zhang, Dinesh Manocha, Bin Zhou

ICCV 2021 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 5 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
train on our part-assisted synthesized data instead of existing front-view dataset2D/3D vehicle parsing network · CVIS test set, 2D detectionmAP: 49.8 -> 53.6Improved
train on our synthesized data instead of rendering data2D/3D vehicle parsing network · CVIS test set, 2D detectionmAP: 46.0 -> 53.6Improved
train on our synthesized data instead of GAN-based data2D/3D vehicle parsing network · CVIS test set, instance segmentationmAP: 37.4 -> 52.4Improved
train on our synthesized data instead of existing dataset2D/3D vehicle parsing network · CVIS test set, 6-DoF poseAbs-mean: 22.4 -> 25.3Improved
use part-based texture inpainting instead of KNN filling (ablation)2D/3D vehicle parsing network · CVIS test set, 2D detectionmAP: 57.5 -> 59.7Improved
use part-based texture inpainting instead of KNN filling (ablation)2D/3D vehicle parsing network · CVIS test set, instance segmentationmAP: 51.1 -> 54.6Improved
use part-based texture inpainting instead of generic image inpainting (ablation)2D/3D vehicle parsing network · CVIS test set, instance segmentationmAP: 47.4 -> 54.6Improved
add vehicle shadows to synthesized data (ablation)2D/3D vehicle parsing network · CVIS test set, 2D detectionmAP: 58.3 -> 59.7Improved
add vehicle shadows to synthesized data (ablation)2D/3D vehicle parsing network · CVIS test set, 6-DoF poseAbs-mean: 30.9 -> 33.0Improved
add vehicle shadows to synthesized data (ablation)2D/3D vehicle parsing network · CVIS test set, instance segmentationmAP: 53.1 -> 54.6Improved
use dense-mapping parsing network (ours) instead of DensePosepose estimation · CVIS test set, 6-DoF poseA3DP-Abs mean: 28.7 -> 38.6Improved
mix our synthesized CVIS data with KITTI training dataMask-RCNN · KITTI 2D detectionmAP: 43.7 -> 45.1Improved

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