AI Paper Atlas

Research map / Point clouds / Segmentation and detection

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li

TPAMI 2020 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 1,007 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
use SparseConvUNet backbone instead of PointNet++ (ablation)Part-A2-free · KITTI val carrecall IoU 0.7 (100 proposals): 74.81 -> 81.54Improved
use RoI-aware pooling instead of fixed-sized RoI pooling (ablation)Part-A2-anchor · KITTI val car3D AP moderate: 78.61 -> 79.47Improved
use sparse conv instead of FC layers in stage-II (ablation)Part-A2-anchor · KITTI val car3D AP moderate: 79.32 -> 79.47No clear effect
increase RoI pooling size from 6 to 14 (ablation)Part-A2-anchor · KITTI val car3D AP moderate: 78.85 -> 79.47Improved
use pooling size 14 instead of 7 with FC layers (ablation)Part-A2-anchor · KITTI val car3D AP moderate: 79.11 -> 79.32Improved
use sparse conv instead of FC at pooling size 7 (ablation)Part-A2-anchor · KITTI val car3D AP moderate: 79.11 -> 79.21Improved
use anchor-based proposals instead of anchor-free (ablation)Part-A2 · KITTI val carrecall IoU 0.7 (50 proposals): 77.12 -> 83.71Improved
anchor-free vs anchor-based proposals (ablation)Part-A2 · KITTI val cyclist and pedestrian3D AP: 73.35 vs 73.07No clear effect
use anchor-based instead of anchor-free proposals for cars (ablation)Part-A2 · KITTI val car3D AP moderate: 78.96 -> 79.47Improved
use bin-based center loss with anchor-free proposals (ablation)Part-A2-free · KITTI val carrecall convergenceImproved
use residual-based center loss with anchor-based proposals (ablation)Part-A2-anchor · KITTI val carrecall convergenceImproved
add intra-object part location supervision (ablation)Part-A2-anchor · KITTI val carrecall and APImproved

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