AI Paper Atlas

Research map / Point clouds / Segmentation and detection

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

Jianyun Xu, Ruixiang Zhang, Jian Dou, Yushi Zhu, Jie Sun, Shiliang Pu

ICCV 2021 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 370 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 range view to voxel+point fusion (RPV vs PV) (ablation)RPVNet · SemanticKITTI valmIoU: 63.8 -> 65.5Improved
add range view to voxel+point fusion (RPV vs PV) (ablation)RPVNet · nuScenes valmIoU: 71.7 -> 73.7Improved
add point view to voxel view (PV vs V) (ablation)RPVNet · SemanticKITTI valmIoU: 63.6 -> 63.8Improved
add range view to point view (RP vs R) (ablation)RPVNet · SemanticKITTI valmIoU: 47.5 -> 50.5Improved
use gated fusion instead of addition (ablation)RPVNet · SemanticKITTI valmIoU: 67.2 -> 68.2Improved
use gated fusion instead of addition (ablation)RPVNet · nuScenes valmIoU: 76.9 -> 77.6Improved
use gated fusion instead of concatenation (ablation)RPVNet · SemanticKITTI valmIoU: 67.4 -> 68.2Improved
use feature-level multi-view fusion instead of softmax model ensemble (ablation)RPV · SemanticKITTI valmIoU: 64.5 -> 68.2Improved
fusion instead of ensemble for PV (ablation)PV · SemanticKITTI valmIoU: 63.9 -> 64.8Improved
add P-branch to V baseline (ablation)RPVNet · SemanticKITTI valmIoU: 64.2 -> 64.8Improved
add R-branch on top of V+P (ablation)RPVNet · SemanticKITTI valmIoU: 64.8 -> 68.2Improved
add instance cut-mix augmentation (ablation)RPVNet · SemanticKITTI valmIoU: 68.2 -> 69.6Improved

Later papers that compared with this method

9 later accepted papers report RPVNet as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

1 more not listed.

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