AI Paper Atlas

Research map / 3D vision / 3D generation

SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation

Sung-Yeon Park, Adam Lee, Juanwu Lu, Can Cui, Luyang Jiang, Rohit Gupta, Kyungtae Han, Ahmadreza Moradipari, Ziran Wang

ECCV 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 2 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 multi-agent path refinement (ablation)SIMSplat · Motion generationfailure rate (%): 53.3 -> 20.0Improved
add multi-agent path refinement (ablation)SIMSplat · Motion generationvehicle collision rate (%): 43.3 -> 13.3Improved
add multi-agent path refinement (ablation)SIMSplat · Motion generationpedestrian collision rate (%): 26.7 -> 16.7Improved
add multi-agent path refinement (ablation)SIMSplat · Motion generationoff-road rate (%): 10.0 -> 6.7Improved
add motion and location features to appearance features (ablation)SIMSplat language alignment · Road object queryingaccuracy and vIoUImproved
add motion features to appearance features (ablation)SIMSplat language alignment · Road object querying (vehicles)accuracy and vIoUImproved
add location features to appearance features (ablation)SIMSplat language alignment · Road object querying (pedestrians)accuracy and vIoUImproved
use motion-aware alignment instead of 4DLangSplatlanguage-aligned Gaussians · Road object querying (vehicles)accuracy: 0.83 accuracy, nearly doubling 4DLangSplatImproved
use motion-aware alignment instead of 4DLangSplatlanguage-aligned Gaussians · Road object querying (pedestrians)accuracy and vIoU: 70.3% and 77.3% higherImproved
replace Qwen3-VL-8B with Qwen3-VL-32B (ablation)VLM-driven scenario mining · Task completiontask completion (%): 48.3 -> 71.1Improved
replace Qwen3-VL-32B with GPT-5 (ablation)VLM-driven scenario mining · Task completiontask completion (%): 71.1 -> 78.9Improved
replace Qwen3-VL-32B with GPT-5 (ablation)VLM-driven scenario mining · Iterationsnumber of iterations: 4.5 -> 3.6Improved

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