AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

Shaoshuai Shi, Li Jiang, Jiajun Deng, Zhe Wang, Chaoxu Guo, Jianping Shi, Xiaogang Wang, Hongsheng Li

IJCV 2022 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 614 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 VectorPool aggregation in VSA and RoI-grid pooling (replacing set abstraction) (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 65.92 -> 66.87Improved
add VectorPool aggregation (reduces memory) (ablation)PV-RCNN++ · Waymo valGPU memory (MB): 10617 -> 7583Improved
use voxel-to-keypoint VSA instead of UNet-decoder with RoI-grid pooling (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 66.05 -> 66.87Improved
use VSA instead of UNet-decoder when combined with RoI-aware pooling (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 65.77 -> 64.31Hurt
replace RoI-aware pooling with RoI-grid pooling (ablation)PV-RCNN++ with VSA · Waymo valmAPH L2 avg: 64.31 -> 66.87Improved
add predicted keypoint weighting (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 66.66 -> 66.87Improved
add proposal-centric keypoint filtering to FPS (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 65.87 -> 66.99Improved
add proposal-centric filtering (faster sampling) (ablation)FPS keypoint sampling · Waymo valsampling time: 133ms -> 27msImproved
use sectorized FPS instead of vanilla FPS after filtering (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 66.99 -> 66.87No clear effect
use sectorized FPS instead of random sampling (ablation)PV-RCNN++ · Waymo valmAPH L2 avg: 63.75 -> 66.87Improved
use interpolation instead of average pooling for sub-voxels (ablation)VectorPool aggregation · Waymo valmAPH L2 avg: 66.06 -> 66.87Improved
use interpolation instead of random selection for sub-voxels (ablation)VectorPool aggregation · Waymo valmAPH L2 avg: 66.29 -> 66.87Improved

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