AI Paper Atlas

Research map / 3D vision / Face and shape

"Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts"

Jianhao Li, Tianyu Sun, Zhongdao Wang, Enze Xie, Bailan Feng, Hongbo Zhang, Ze Yuan, Ke Xu, Jiaheng Liu, Ping Luo

ECCV 2024 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 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
add point cloud alignment term to mask alignment term (ablation)SLF · KITTI val CarAP_3D Easy: 6.9 -> (valid results)Improved
add mask alignment term on top of point cloud alignment (ablation)SLF · KITTI val CarAP_3DImproved
add ground alignment term (ablation)SLF · KITTI val CarAP_3DImproved
increase PCA shape dimension from 3 to 5 (ablation)SLF · KITTI val CarAP_3DImproved
increase PCA dimension from 5 to 10 (ablation)SLF · KITTI val CarAP_3DNo clear effect
use more CAD models for PCA shape prior (5, 30, to 79) (ablation)SLF · KITTI val CarAP_3DImproved
increase SAM prompt points from 3 to 8 (ablation)SLF_point · KITTI val CarAP_3DNo clear effect
use 1 point prompt instead of 3 (ablation)SLF_point · KITTI val Car EasyAP_3DHurt
replace human ground-truth masks with SAM masks from box prompts (ablation)SLF · KITTI val CarAP_3D / AP_BEV: Mod. AP_3D 87.8 -> 88.2; Hard 83.8 -> 83.9; Easy 87.6 -> 87.9Mixed
train detectors on SLF pseudo labels instead of FGR pseudo labelsOpenPCDet detectors · KITTI val CarAP_3D Moderate/Hard: PointPillar Mod. 89.4 -> 92.1Improved
use SLF instead of supervised MTrans for cross-dataset labelingauto-labeler · nuScenes valmAP: 45.9 -> 57.2Improved
downsample LiDAR from 64 to fewer beams (ablation)SLF · KITTI val CarAP_3DHurt

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