AI Paper Atlas

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

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

Changyong Shu, Jiajun Deng, Fisher Yu, Yifan Liu

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 48 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
replace camera-ray PE with oracle 3D point PE using ground-truth depth (ablation)PETR-style detector · nuScenes valNDS: 0.337 -> 0.404Improved
replace camera-ray PE with LiDAR-ray PE (ablation)PETR-style detector · nuScenes valNDS: 0.337 -> 0.338No clear effect
add smooth-L1 depth supervision (ablation)3DPPE · nuScenes valNDS: 0.343 -> 0.365Improved
add distribution focal loss on top of smooth-L1 (ablation)3DPPE · nuScenes valNDS: 0.365 -> 0.368Improved
use depth-guided single 3D point PE instead of camera-ray PE (ablation)3DPPE · nuScenes valNDS: 0.337 -> 0.368Improved
use top-5 depth bins instead of one predicted depth point (ablation)3DPPE · nuScenes valNDS: 0.368 -> 0.327Hurt
add depth feature into positional encoding (ablation)3DPPE · nuScenes valNDS: 0.368 -> 0.359Hurt
share 3D point PE encoder between image features and object queries (ablation)3DPPE · nuScenes valNDS: 0.362 -> 0.368Improved
add temporal modeling (3DPPE-v2) versus PETR-v23DPPE · nuScenes valNDS: 0.502 -> 0.524Improved
add knowledge distillation from oracle-depth model3DPPE · nuScenes valNDS: 0.440 -> 0.454Improved
replace PETR camera-ray PE with 3DPPE point PEPETR · nuScenes testmAP: 0.441 -> 0.460Improved

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