AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception

Xiao Zhao, Chang Liu, Mingxu Zhu, Zheyuan Zhang, Linna Song, Qingliang Luo, Chufan Guo, Kuifeng Su

ICLR 2026 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 0 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
replace BEV grid fusion with unified 3D Gaussian fusionBEVFusion · nuScenes val detectionNDS: 71.4 -> 74.0Improved
Gaussian representation instead of BEV grid on WaymoBEVFusion · Waymo Open DatasetmAP-L1: 82.72 -> 86.23Improved
Gaussian representation at low resolution (100x100)BEVFusion · nuScenes valNDS: 70.5 -> 73.1Improved
increase BEV size 100x100 to 400x400 (ablation)BEVFusion · nuScenes valNDS: 70.5 -> 72.7Improved
increase BEV size 100x100 to 400x400 (ablation)GaussianFusion · nuScenes valNDS: 73.1 -> 74.4No clear effect
forward-projection Gaussian init vs random init (ablation)GaussianFusion · nuScenes valNDS: 71.2 -> 74.0Improved
forward-projection init vs backward projection (ablation)GaussianFusion · nuScenes valNDS: 72.4 -> 74.0Improved
forward-projection init vs Lidar projection init (ablation)GaussianFusion · nuScenes valNDS: 73.6 -> 74.0No clear effect
use shared Gaussian encoder instead of separate (ablation)GaussianFusion · nuScenes valmAP: 71.0 -> 71.7Improved
add Gaussian priors to deformable attention (ablation)GaussianFusion · nuScenes valNDS: 73.6 -> 74.0Improved
encode Gaussian properties as positional encoding in query (ablation)GaussianFusion · nuScenes valmAP: 71.2 -> 71.7Improved
predict property offsets instead of new properties (ablation)GaussianFusion · nuScenes valmAP: 70.8 -> 71.7Improved

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