AI Paper Atlas

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

OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

Jinghua Hou, Tong Wang, Xiaoqing Ye, Zhe Liu, Shi Gong, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 21 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 pixel-wise depth supervision (PDE) alone to StreamPETR (ablation)StreamPETR · nuScenes valmAP: 50.3 -> 50.5No clear effect
add object-wise position embedding (OPE) in transformer decoder (ablation)OPEN · nuScenes valNDS: 59.7 -> 60.8Improved
add depth-aware focal loss (DFL) (ablation)OPEN · nuScenes valNDS: 60.8 -> 61.3 NDS; 52.4 -> 52.1 mAPMixed
add object-wise depth encoder (ODE) on top of PDE (ablation)OPEN · nuScenes valNDS: 59.4 -> 59.7Improved
use temporal information in ODE (ablation)OPEN · nuScenes valNDS: 61.0 -> 61.3Improved
add pixel-wise depth encoder as prior for object-wise depth (ablation)OPEN · nuScenes valNDS: 59.9 -> 61.3Improved
object-wise position embedding vs point-aware PE (3DPPE) (ablation)OPEN · nuScenes valNDS: 60.0 -> 60.8Improved
object-wise position embedding vs ray-aware PE on distant objects (ablation)StreamPETR baseline · nuScenes val, objects beyond 40mNDS: 36.8 -> 39.1Improved
predict object-wise depth instead of pixel-wise depthdepth prediction · nuScenes val, objects beyond 40mL1 error (m): 12.28 -> 3.88Improved
apply OPEN to StreamPETR with ViT-L backbone at 48 epochsStreamPETR · nuScenes val (ViT-L)NDS: 61.3 -> 62.5Improved
apply OPEN to single-frame PETRPETR · nuScenes val single frameNDS: 45.5 -> 50.3Improved

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