AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SEED: A Simple and Effective 3D DETR in Point Clouds

Zhe Liu, Jinghua Hou, Xiaoqing Ye, Tong Wang, Jingdong Wang, Xiang Bai

ECCV 2024 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 16 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 heatmap-based query selection with dual query selection (DQS) (ablation)SEED-S · Waymo val (20% train)mAPH L2: 64.6 -> 67.4Improved
replace box attention with deformable grid attention (DGA) (ablation)SEED-S · Waymo val (20% train)mAPH L2: 64.6 -> 66.4Improved
combine DQS and DGA (ablation)SEED-S · Waymo val (20% train)mAPH L2: 64.6 -> 68.2Improved
use DQS instead of learnable or Top-N query selection (ablation)SEED-S · Waymo val (20% train)mAPH L2: 66.6 -> 68.2 (learnable); 66.8 -> 68.2 (Top-N)Improved
use heatmap-based query selection (ablation)SEED-S · Waymo val (20% train)mAPH L2: 68.2 -> 65.0Hurt
use deformable grid attention instead of global attention (ablation)SEED-S · Waymo val (20% train)feasibility: OOM -> 68.2 mAPH L2Improved
use deformable grid attention instead of deformable or box attention (ablation)SEED-S · Waymo val (20% train)mAPH L2: 67.5 -> 68.2Improved
use quality-aware Hungarian matching instead of traditional matching (ablation)SEED-S · Waymo val (20% train)mAPH L2: 67.6 -> 68.2Improved
use SEED-L over DSVT-Voxel on Waymo valWaymo val single frame · Waymo val (100% train)mAPH L2: 72.1 -> 73.5Improved
use SEED instead of TransFusion-L on nuScenes with the same 3D backbonenuScenes val · nuScenes valNDS / mAP: 70.1 -> 71.2 NDS; 65.1 -> 66.6 mAPImproved
use higher-resolution SEED-L over SEED-BPedestrian detection · Waymo val (100% train)Pedestrian APH L2: 70.8 -> 71.8Improved

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