AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han

ECCV 2020 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 817 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 high-resolution point-based branch to Sparse Convolution (SPVCNN vs MinkowskiNet) (ablation)MinkowskiNet · SemanticKITTI test (smallest scale)mIoU: 57.5 -> 58.5Improved
add point-based branch (SPVCNN vs MinkowskiNet) (ablation)MinkowskiNet · SemanticKITTI test (5.5M params)mIoU: 60.0 -> 61.6Improved
add point-based branch (SPVCNN vs MinkowskiNet) (ablation)MinkowskiNet · SemanticKITTI val seq 08 (21.7M params)mIoU: 61.1 -> 63.8Improved
add point-based branch (SPVCNN vs MinkowskiNet) (ablation)MinkowskiNet · SemanticKITTI test (21.7M params)mIoU: 63.1 -> 63.8Improved
add 3D-NAS to SPVCNN (SPVNAS vs SPVCNN) (ablation)SPVCNN · SemanticKITTI test (smallest scale)mIoU: 58.5 -> 63.6Improved
use SPVNAS instead of MinkowskiNetMinkowskiNet · SemanticKITTI testmIoU: 63.1 -> 66.4Improved
add point-based branch to Sparse Convolution on small classes (ablation)MinkowskiNet · SemanticKITTI test MotorcyclistIoU: 18.7 -> 43.7Improved
add point-based branch to Sparse Convolution on small classes (ablation)MinkowskiNet · SemanticKITTI test BicyclistIoU: 61.9 -> 65.2Improved
replace 3D sparse convolutions in SECOND with SPVConv (ablation)SECOND (Repro.) · KITTI test Cyclist moderatemAP: 59.7 -> 63.7Improved
replace 3D sparse convolutions in SECOND with SPVConv (ablation)SECOND (Repro.) · KITTI test Pedestrian moderatemAP: 41.7 -> 41.4No clear effect
replace 3D sparse convolutions in SECOND with SPVConv (ablation)SECOND · KITTI val Pedestrian easymAP: 68.3 -> 68.2No clear effect
use evolutionary search instead of random search (ablation)3D-NAS · SemanticKITTI valmIoU: around 3% better than first generationImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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