AI Paper Atlas

Research map / Point clouds / Segmentation and detection

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

Youquan Liu, Runnan Chen, Xin Li, Lingdong Kong, Yuchen Yang, Zhaoyang Xia, Yeqi Bai, Xinge Zhu, Yuexin Ma, Yikang Li, Yu Qiao, Yuenan Hou

ICCV 2023 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 96 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 RGB image fusion via LMA on top of voxel+point+range views (ablation)UniSeg · SemanticKITTI valmIoU: 69.7 -> 71.3Improved
replace early-fusion addition with LMA deformable cross-attention fusion (ablation)UniSeg · SemanticKITTI valmIoU: 70.1 -> 71.3Improved
use input concatenation fusion instead of addition (ablation)early fusion · SemanticKITTI valmIoU: 70.1 -> 69.4Hurt
use PointPainting or PointAugmenting instead of LMA (ablation)UniSeg · SemanticKITTI valmIoU: 70.1 -> 70.5No clear effect
add LVA learnable cross-view fusion instead of addition (ablation)UniSeg · SemanticKITTI valmIoU: 70.4 -> 71.3Improved
use LMA instead of addition under noisy calibration matrices (ablation)UniSeg · SemanticKITTI valmIoU: 68.5 -> 71.0Improved
use voxel view only versus range view only (ablation)single-view baseline · SemanticKITTI valmIoU: 55.8 -> 68.4Improved
prune 80% channels per layer (UniSeg 0.2x) (ablation)UniSeg · SemanticKITTI valmIoU: 71.3 -> 67.0Hurt
use UniSeg versus Panoptic-PHNet for nuScenes panopticUniSeg · nuScenes test (panoptic)PQ: 81.5 -> 78.4Hurt
reimplement methods in OpenPCSeg codebaseMinkowskiNet · SemanticKITTI valmIoU: 61.1 -> 68.8Improved

Later papers that compared with this method

1 later accepted paper reports UniSeg as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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