AI Paper Atlas

Research map / 3D vision / 3D generation

Viewpoint Equivariance for Multi-View 3D Object Detection

Dian Chen, Jie Li, Vitor Guizilini, Rares Andrei Ambrus, Adrien Gaidon

CVPR 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 32 citations (OpenAlex)

This paper tried a common change: Add positional encoding

add Fourier+MLP geometric positional encoding and object queries (replacing PETR's encodings) · NuScenes val · mAP: +1.6% mAP (0.404 to 0.420) Improved

What 646 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 Fourier+MLP geometric positional encoding and object queries (replacing PETR's encodings) (ablation)PETR-style single-frame detector · NuScenes valmAP: +1.6% mAP (0.404 to 0.420)Improved
add 2 virtual query views with viewpoint equivariance (joint matching and loss) (ablation)VEDet single-frame with geometric PE · NuScenes valmAP: +1.4% mAP (0.420 to 0.434)Improved
add 2 virtual query views with viewpoint equivariance (ablation)VEDet 2-frame · NuScenes valmAP: +1.9% mAP (0.432 to 0.451)Improved
add 2-frame temporal modeling (ablation)VEDet with geometric PE only · NuScenes valmAP: +1.2% mAP (0.420 to 0.432)Improved
add the extra queries and duplicated box targets without viewpoint equivariance (+2M qry, no VE) (ablation)VEDet V=0 · NuScenes valmAPNo clear effect
remove Fourier encoding before the MLP (ablation)VEDet · NuScenes valmAP: -6.9% mAP (0.451 to 0.382)Hurt
remove camera translation from geometric encoding (ablation)VEDet · NuScenes valmAP: -9.2% mAP (0.451 to 0.353)Hurt
remove camera rotation from geometric encoding (ablation)VEDet · NuScenes valmAP: -1.5% mAP (0.451 to 0.436)Hurt
treat multi-view predictions of same query as individual objects (no joint matching) (ablation)VEDet · NuScenes valmAP: -2.6% mAP (0.451 to 0.425)Hurt
number of virtual query views V increased from 0 to 2 (ablation)VEDet · NuScenes valmAP: 0.432 to 0.451 mAPImproved
number of virtual query views increased to 6 (ablation)VEDet · NuScenes valmAP: 0.451 to 0.437 mAPHurt
VEDet vs PETR and PETRv2 at Res-50/Res-101 and V2-99 settingsVEDet · NuScenes valmAP: +2.0% mAP over PETRv2 (0.451 vs 0.431)Improved

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