AI Paper Atlas

Research map / 3D vision / 3D generation

Communication-Efficient Multi-Vehicle Collaborative Semantic Segmentation via Sparse 3D Gaussian Sharing

Tianyu Hong, Xiaobo Zhou, Wenkai Hu, Qi Xie, Zhihui Ke, Tie Qiu

ICCV 2025 · 3D vision › 3D generation · approach: Semantic scene completion · 4 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 Semantic Gaussian Compression (learnable codebook indices) on top of selection (ablation)GSCOOP · OPV2Vcommunication volume (KB) and vehicle IoU: 34.18 -> 15.87 KB; vehicle IoU 57.39 -> 57.21Improved
combine relevance-projection and semantic-uncertainty priority scores for Gaussian selection (ablation)GSCOOP · OPV2Vvehicle IoU: 56.84 -> 57.39 (vs first single-module row), 55.20 -> 57.39 (vs second)Improved
use codebook size 64 instead of 8 (ablation)GSCOOP · OPV2Vvehicle IoU: 53.31 -> 57.21Improved
increase codebook size from 64 to 256 (ablation)GSCOOP · OPV2Vvehicle IoU: 57.21 -> 54.79Hurt
increase codebook size from 64 to 128 (ablation)GSCOOP · V2X-Seqavg IoU: 60.49 -> 58.15Hurt
use 100*100*4 initial Gaussian voxels instead of 100*100*8 (ablation)GSCOOP · OPV2Vvehicle IoU: 55.33 -> 57.21Improved
use 100*100*4 initial Gaussian voxels instead of 80*80*4 (ablation)GSCOOP · V2X-Seqavg IoU: 54.63 -> 60.49Improved
add scale and rotation attributes to transmitted Gaussians (position only vs all) (ablation)GSCOOP Gaussian attributes · OPV2Vvehicle IoU and volume (KB): 57.21 -> 58.06 IoU; 15.87 -> 50.05 KBNo clear effect
transmit position attributes versus semantics only (ablation)GSCOOP Gaussian attributes · OPV2Vvehicle IoU and volume (KB): 52.38 -> 57.21 IoU; 1.22 -> 15.87 KBImproved
sparse Gaussian sharing instead of dense BEV feature sharing (GSCOOP vs CoBEVT)collaborative BEV segmentation · OPV2Vavg IoU: 49.90 -> 56.20Improved
sparse Gaussian sharing instead of dense BEV feature sharing (GSCOOP vs ERMVP)collaborative BEV segmentation · V2X-Seqavg IoU: 56.48 -> 60.49Improved
Gaussian-based fusion instead of BEV feature fusion network (GSCOOP vs CoBEVT)inference time with 7 vehicles · OPV2Vinference time (ms): 511.32 -> 242.35 msImproved

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