AI Paper Atlas

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

FrustumFormer: Adaptive Instance-Aware Resampling for Multi-View 3D Detection

Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang

CVPR 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 28 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 FrustumFormer instead of PolarFormernuScenes test with ResNet101-DCN · nuScenes testmAP: 0.457 -> 0.478Improved
Use FrustumFormer instead of PETRv2nuScenes test with VoVNet-99 · nuScenes testmAP: 0.490 -> 0.516Improved
Add instance frustum queries (ablation)FrustumFormer baseline · nuScenes val ablationmAP: 0.318 -> 0.326Improved
Add occupancy mask prediction (ablation)FrustumFormer baseline · nuScenes val ablationmAP: 0.318 -> 0.328Improved
Add instance frustum queries and occupancy mask (ablation)FrustumFormer baseline · nuScenes val ablationmAP: 0.318 -> 0.337Improved
Add temporal frustum fusion (ablation)Adaptive instance-aware resampling · nuScenes val ablationNDS: 0.383 -> 0.463Improved
Double sampling points uniformly across scene regions (ablation)FrustumFormer baseline sampling · nuScenes val ablationmAP: 0.318 -> 0.318No clear effect
Allocate extra sampling to instance regions rather than uniformly (ablation)FrustumFormer baseline sampling · nuScenes val ablationmAP: 0.318 -> 0.326Improved
Use strict projected boxes instead of enlarged boxes for occupancy supervision (ablation)Occupancy mask learning · nuScenes val ablationmAP: 0.324 -> 0.328Improved
Increase occupancy mask loss weight from 5.0 to 10.0 (ablation)Occupancy mask learning · nuScenes val ablationmAP: 0.328 -> 0.322Hurt
Decrease occupancy mask loss weight from 5.0 to 1.0 (ablation)Occupancy mask learning · nuScenes val ablationmAP: 0.328 -> 0.326Hurt
Increase temporal window from 8 to 16 with 4 keyframes (ablation)Temporal frustum fusion · nuScenes val ablationmAP: 0.360 -> 0.364Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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