AI Paper Atlas

Research map / Point clouds / Segmentation and detection

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia

ICCV 2019 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 894 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 the 3D IoU branch (cls-score x predicted IoU for NMS) instead of plain NMS (ablation)STD · KITTI val CarAP 3D moderate (%): 78.7 -> 79.8Improved
add 3D IoU branch instead of Soft-NMS (ablation)STD · KITTI val CarAP 3D moderate (%): 79.0 -> 79.8Improved
multiply classification score with predicted IoU instead of using predicted 3D IoU alone for NMS (ablation)STD · KITTI val CarAP 3D moderate (%): 79.1 -> 79.8Improved
use oracle IoU instead of classification score for NMS sorting (ablation)STD · KITTI val CarAP 3D moderate (%): 78.7 -> 90.9Improved
add semantic segmentation features to proposal features (ablation)STD · KITTI val CarAP 3D moderate (%): 31.1 -> 67.6Improved
add canonical coordinates to proposal features (ablation)STD · KITTI val CarAP 3D moderate (%): 67.6 -> 78.7Improved
use spherical anchors instead of single-orientation cuboid anchors (ablation)STD proposal generation · KITTI val Carrecall IoU=0.7: 74.2 -> 76.8Improved
use spherical anchors instead of 2x cuboid anchors (ablation)STD proposal generation · KITTI val Carrecall IoU=0.7: 75.7 -> 76.8Improved
replace PointNet head with PointsPool + 2FC (ablation)STD box head · KITTI val CarAP 3D moderate (%): 77.1 -> 78.7Improved
replace PointNet++ head with PointsPool + 2FC (ablation)STD box head · KITTI val CarAP 3D moderate (%): 79.1 -> 78.7Mixed
merge batch norm into conv layers and split first SA input into 32 x 512 for parallel computation (ablation)STD · KITTI val Carinference time: 25ms and 50ms speedupNo clear effect
add spherical anchors proposal generationSTD · KITTI val Carrecall IoU=0.5, 50 proposals: 91.0 -> 96.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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