AI Paper Atlas

Research map / Point clouds / Segmentation and detection

3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection

Alexander Lehner, Stefano Gasperini, Alvaro Marcos-Ramiro, Michael Schmidt, Mohammad-Ali Nikouei Mahani, Nassir Navab, Benjamin Busam, Federico Tombari

CVPR 2022 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 65 citations (OpenAlex)

Check 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 sensor-aware adversarial vector-field augmentationPointPillars · Waymo val, transfer from KITTIAP: 40.86 -> 44.61Improved
Add sensor-aware adversarial vector-field augmentationPointPillars · CrashD rare crash, transfer from KITTIAP: 22.48 -> 30.37Improved
Add sensor-aware adversarial vector-field augmentationPointPillars · KITTI val, car, moderateAP: 77.11 -> 77.13No clear effect
Add 3D-VField augmentationSecond · Waymo val, transfer from KITTIAP: 42.45 -> 43.51Improved
Add 3D-VField augmentationPart-A² · Waymo val, transfer from KITTIAP: 49.76 -> 56.08Improved
Add statistical normalization domain adaptation to 3D-VFieldPointPillars · CrashD rare crash, transfer from KITTIAP: 48.23 -> 76.42Improved
Use 12 rather than 1 relative-rotation group (ablation)3D-VField · Waymo, transfer from KITTIAP: 40.43 -> 44.61Improved
Use 360 rather than 12 relative-rotation groups (ablation)3D-VField · Waymo, transfer from KITTIAP: 44.61 -> 40.30Hurt
Do not learn the perturbation; apply the constraints (ablation)3D-VField · Waymo, transfer from KITTIAP: 41.62 vs 40.86No clear effect
Remove all deformation constraints (ablation)3D-VField · CrashD rare crash, transfer from KITTIAP: 27.55 vs 30.37Hurt
Apply sensor-ray constraint without distance smoothing (ablation)3D-VField · CrashD rare crash, transfer from KITTIAP: 29.16 vs 30.37Hurt
Increase maximum deformation from 30 cm to 40 cm or 60 cm (ablation)3D-VField · KITTIAP: 1% and 1.7%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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