AI Paper Atlas

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

Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry

Shengjie Zhu, Girish Chandar Ganesan, Abhinav Kumar, Xiaoming Liu

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection

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
apply RePLAy artifact removal instead of the modified half-occlusion baseline to LiDAR depthmapsLiDAR projected depthmap · KITTI Stereo GT (foreground)delta_0.5: 0.919 -> 0.925Improved
add auto-calibration of the virtual LiDAR camera origin (ablation)RePLAy · KITTI Eigen semi-dense GT (all)SIlog: 5.680 -> 4.592Improved
train ZoeDepth on RePLAy-cleaned depthmaps instead of rawZoeDepth · KITTI Eigen (from scratch)SIlog: 13.501 -> 8.674Improved
train ZoeDepth on RePLAy depthmaps instead of raw on datasets without stereoZoeDepth · nuScenes Val (foreground)SIlog: 6.339 -> 4.905Improved
train ZoeDepth on RePLAy depthmaps instead of rawZoeDepth · Waymo Val (foreground)SIlog: 9.116 -> 7.322Improved
use RePLAy depthmaps instead of raw, across rain, night, sunny conditionsZoeDepth · nuScenes Val by conditionSIlog: Night 7.481 -> 5.374Improved
train ZoeDepth on RePLAy instead of semi-dense GTZoeDepth · KITTI Stereo (all)SIlog: 7.971 -> 8.588Mixed
retrain CaDDN with RePLAy-cleaned depthmapsCaDDN · KITTI Val Car AP3DAP3D: Easy 21.60 -> 22.88; Hard 13.24 -> 13.18Mixed
retrain MonoDTR with RePLAy-cleaned depthmapsMonoDTR · KITTI Val Car AP3DAP3D: Easy 24.50 -> 26.15; Mod 18.66 -> 18.77; Hard 15.69 -> 15.69Improved

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