AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Bridged Transformer for Vision and Point Cloud 3D Object Detection

Yikai Wang, TengQi Ye, Lele Cao, Wenbing Huang, Fuchun Sun, Fengxiang He, Dacheng Tao

CVPR 2022 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 58 citations (OpenAlex)

Check 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
Bridge image and point features with conditional queries, shared positional embeddings, and point-to-patch projection (ablation)BrT · SUN RGB-DmAP@0.25: 62.6 -> 65.4Improved
Bridge image and point features with conditional queries, shared positional embeddings, and point-to-patch projection (ablation)BrT · SUN RGB-DmAP@0.5: 44.3 -> 48.1Improved
Use conditional object queries together with shared positional embeddings (ablation)BrT · SUN RGB-DmAP@0.25: 62.6 -> 64.0Improved
Use conditional object queries together with shared positional embeddings (ablation)BrT · SUN RGB-DmAP@0.5: 44.3 -> 46.3Improved
Add point-to-patch projection (ablation)BrT · SUN RGB-DmAP@0.25: 62.6 -> 64.2Improved
Add point-to-patch projection (ablation)BrT · SUN RGB-DmAP@0.5: 44.3 -> 46.6Improved
Use ImageNet-1k ViT-S pre-training rather than training from scratch (ablation)BrT · SUN RGB-DmAP@0.25: 62.8 -> 65.4Improved
Use COCO-finetuned YOLOS-S initialization instead of ImageNet-1k ViT-S initialization (ablation)BrT · SUN RGB-DmAP@0.25: 65.4 -> 63.4Hurt
Directly append 3-dimensional RGB values to Group-Free point featuresGroup-Free · SUN RGB-DmAP@0.25: 63.0 -> 61.7Hurt
Add Faster R-CNN region features to Group-Free seed pointsGroup-Free · ScanNetV2mAP@0.25: 69.1 -> 68.7No clear effect
Use ViT-B/16 rather than ViT-S/16BrT · ScanNetV2mAP@0.25: 69.7 -> 71.3Improved
Allow direct attention connections between point tokens and image patch tokens (ablation)BrT · SUN RGB-DmAP@0.25: 65.4 -> 63.9Hurt

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