AI Paper Atlas

Research map / 3D vision / 3D generation

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

Tianchen Deng, Xuefeng Chen, Yi Chen, Qu Chen, Yuyao Xu, Lijin Yang, Le Xu, Yu Zhang, Bo Zhang, Wuxiong Huang, Hesheng Wang

CVPR 2026 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 12 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 3D Gaussian tokens to the fine-tuned LLM (ablation)GaussianDWM · NuInteractAvg score: 53.32 -> 55.21 (random sampling)Improved
replace random sampling with top-k + uniform sampling of Gaussians (ablation)GaussianDWM · NuInteractAvg score: 55.21 -> 58.93Improved
add similarity-based language-guided sampling (ablation)GaussianDWM · NuInteractAvg score: 58.93 -> 59.23Mixed
fine-tune the model on NuInteract (ablation)GaussianDWM · NuInteractAvg score: 15.39 -> 53.32Improved
add high-level LLM language condition to low-level image condition (ablation)GaussianDWM generator · nuScenes spatial generationFID +-1m / +-2m: 10.12 -> 8.36 (+-1m); 45.14 -> 44.5 (+-2m)Improved
use only high-level language condition without image condition (ablation)GaussianDWM generator · nuScenes spatial generationFID: failureHurt
GaussianDWM vs DriveMonkey on planning and region descriptionGaussianDWM · NuInteractPlanning Acc / CIDEr: 82.64 -> 80.95 Acc; 79.79 -> 78.72 CIDErHurt
GaussianDWM vs DiST-S at large viewpoint shiftGaussianDWM · nuScenes spatial generation (+-4m)FID / FVD: 17.57 -> 18.81 FID; 105.29 -> 116.40 FVDHurt

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