AI Paper Atlas

Research map / 3D vision / Depth and stereo

View Consistent Purification for Accurate Cross-View Localization

Shan Wang, Yanhao Zhang, Akhil Perincherry, Ankit Vora, Hongdong Li

ICCV 2023 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 16 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 two confidence maps (view-consistent and on-ground) instead of one merged map (ablation)PureACL · FordAV-CVL Log4yaw mean error (deg): 2.08 -> 0.90Improved
add camera-aware spatial embedding (ablation)PureACL · FordAV-CVL Log4longitudinal mean error (m): 1.17 -> 0.88Improved
use view-consistent on-ground keypoint detector instead of SuperPoint (ablation)PureACL · FordAV-CVL Log4yaw mean error (deg): 1.05 -> 0.74Improved
use highest-confidence multi-camera fusion instead of mean fusion (ablation)PureACL · FordAV-CVL Log4yaw mean error (deg): 0.90 -> 0.74Improved
increase onboard cameras from 1 front to 4 (ablation)PureACL · FordAV-CVL Log4yaw mean error (deg): 2.77 -> 0.74Improved
use two side cameras instead of front and rear cameras (ablation)PureACL · FordAV-CVL Log4yaw mean error (deg): 1.14 -> 3.56Hurt
sparse visual-only method versus LiDAR-visual SIBCL on translationPureACL · KITTI-CVLlateral mean error (m): 1.02 -> 0.14Improved
sparse visual-only method versus LiDAR-visual SIBCL on orientationPureACL · KITTI-CVLyaw mean error (deg): 1.91 -> 3.57Hurt
PureACL generalization to unseen roadPureACL · FordAV-CVL Log4->5longitudinal mean error (m): 6.27 -> 1.43Improved
larger initial pose perturbation up to 60 degree yaw or 15 m shift (ablation)PureACL · KITTI-CVL initial poselateral mean error (m): 0.17 -> 3.98 (15m, 15 deg versus 15m, 7.5 deg)Hurt

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