AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection

Tianyu Wang, Xiaowei Hu, Zhengzhe Liu, Chi-Wing Fu

NeurIPS 2022 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 8 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 Sparse2Dense to SECONDSECOND · Waymo Open validation, Vehicle-L2mAP: 59.42 -> 63.49Improved
Add Sparse2Dense to CenterPoint-PillarCenterPoint-Pillar · Waymo Open validation, Vehicle-L2mAP: 64.12 -> 68.11Improved
Add Sparse2Dense to CenterPointCenterPoint · Waymo Open validation, Vehicle-L2mAP: 65.52 -> 68.21Improved
Add Sparse2Dense to CenterPoint-VoxelCenterPoint-Voxel · Waymo Domain Adaptation, Vehicle-L2mAP: 48.36 -> 51.01Improved
Add feature and heat-map distillation (ablation)CenterPoint · Waymo Open validation, Vehicle-L2mAP: 63.03 -> 63.84Improved
Add the S2D module to the distillation variant (ablation)CenterPoint · Waymo Open validation, Vehicle-L2mAP: 63.84 -> 65.75Improved
Add PCR to the S2D variant (ablation)CenterPoint · Waymo Open validation, Vehicle-L2mAP: 65.75 -> 66.12Improved
Add PCR to the S2D variant (ablation)CenterPoint · Waymo Open validation, Pedestrian-L2mAP: 67.62 -> 67.47Hurt
Add PCR to the S2D variant (ablation)CenterPoint · Waymo Open validation, Cyclist-L2mAP: 68.50 -> 68.69Improved
Add the S2D module to the distillation variant (ablation)CenterPoint · Waymo Open validation, Pedestrian-L2mAP: 67.04 -> 67.62Improved
Add the S2D module to the distillation variant (ablation)CenterPoint · Waymo Open validation, Cyclist-L2mAP: 67.59 -> 68.50Improved
Add feature and heat-map distillation (ablation)CenterPoint · Waymo Open validation, Cyclist-L2mAP: 65.03 -> 67.59Improved

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