AI Paper Atlas

Research map / 3D vision / 3D generation

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Yiyi Liao, Jun Xie, Andreas Geiger

TPAMI 2022 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 898 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
add 3D points terms to local appearance (ablation)LA label transfer model · KITTI-360 label transfer (static)semantic mIoU: 67.6 -> 70.4Improved
add 3D points terms to local appearance (ablation)LA label transfer model · KITTI-360 label transfer (static)instance mIoU: 72.3 -> 72.9Improved
add 2D pairwise constraints to local appearance (ablation)LA label transfer model · KITTI-360 label transfer (static)semantic mIoU: 67.6 -> 66.6Hurt
add 3D primitive constraints to LA+PW (ablation)LA+PW · KITTI-360 label transfer (static)semantic mIoU: 66.6 -> 76.8Improved
add 3D points terms to LA+PW+CO (ablation)LA+PW+CO · KITTI-360 label transfer (static)semantic mIoU: 76.8 -> 78.2Improved
add 3D pairwise constraints (full model) (ablation)LA+PW+CO+3D · KITTI-360 label transfer (static)semantic mIoU: 78.2 -> 81.2Improved
add 3D pairwise constraints (full model) (ablation)LA+PW+CO+3D · KITTI-360 label transfer (static)instance mIoU: 83.6 -> 83.7No clear effect
predict only the 70% most certain pixelsFull Model · KITTI-360 label transfer (static)semantic mIoU: 81.2 -> 94.3Improved
predict only the 70% most certain pixelsFull Model · KITTI-360 label transfer (static)instance mIoU: 83.7 -> 92.7Improved
use 3D points projection instead of 3D primitives before graph cuts3D to 2D baselines · KITTI-360 label transfer (static)semantic mIoU: 49.4 -> 72.6Improved
proposed method vs best 2D label transfer baselineLabel transfer · KITTI-360 label transfer (dynamic)mIoU: 37.2 -> 63.5Improved
use deeper ResNet-101 backbone instead of ResNet-50Mask R-CNN · KITTI-360 2D instance segmentationAP: 19.5 -> 20.9Improved

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