AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing

NeurIPS 2023 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 5 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 bidirectional propagation to single-modal point branch (ablation)UPIDet · KITTI valmAP: 75.88 -> 78.64Improved
add point-to-pixel propagation used only in training (ablation)single-modal UPIDet · KITTI valmAP: 75.88 -> 77.01Improved
add pixel-to-point propagation only (ablation)single-modal UPIDet · KITTI valmAP: 75.88 -> 77.47Improved
add point-to-pixel on top of pixel-to-point (ablation)UPIDet · KITTI valmAP: 77.47 -> 78.64Improved
add 3D segmentation and center estimation auxiliary tasks (ablation)LiDAR-only branch · KITTI valmAP: 75.18 -> 75.88Improved
add 3D segmentation alone (ablation)LiDAR-only branch · KITTI valmAP: 75.18 -> 75.07No clear effect
add image branch without 2D auxiliary tasks (ablation)UPIDet · KITTI valmAP: 75.88 -> 76.38Improved
add 2D semantic segmentation (ablation)UPIDet with image branch · KITTI valmAP: 76.38 -> 77.18Improved
add NLC map estimation (ablation)UPIDet with 2D seg · KITTI valmAP: 77.18 -> 78.64Improved
apply bidirectional propagation to SASA asymmetric backboneSASA · KITTI valmAP: 75.24 -> 76.61Improved
use image semantics in semantic-guided SA sampling (ablation)UPIDet · KITTI SA Level-2foreground rate: 15.87 -> 20.70Improved
joint 2D-3D learning vs single-modal 2D segmentationPSPNet · KITTI 2D segmentationmIoU: 43.92 -> 48.34Improved

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