AI Paper Atlas

Research map / 3D vision / Gaussian splatting

HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving

Hongyu Zhou, Longzhong Lin, Jiabao Wang, Yichong Lu, Dongfeng Bai, Bingbing Liu, Yue Wang, Andreas Geiger, Yiyi Liao

TPAMI 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 68 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 box optimization with the unicycle model instead of noisy boxes (ablation)HUGSIM dynamic reconstruction · KITTI (5% noise)PSNR: 23.83 -> 28.78Improved
add unicycle model to per-frame box optimization (ablation)HUGSIM dynamic reconstruction · KITTI (5% noise)PSNR: 24.80 -> 28.78Improved
add unicycle model to per-frame box optimization (ablation)HUGSIM dynamic reconstruction · KITTI (20% noise)translation error: 0.612 -> 0.176Improved
add naive per-frame box optimization without unicycle model (ablation)HUGSIM dynamic reconstruction · KITTI (5% noise)translation error: 0.027 -> 0.051Hurt
add affine exposure transform (ablation)HUGSIM static reconstruction · KITTI-360 static scenesPSNR: 24.18 -> 24.52Improved
add semantic loss L_S (ablation)HUGSIM static reconstruction · KITTI-360 static scenesPSNR: 24.47 -> 24.52No clear effect
add semantic loss L_S (ablation)HUGSIM static reconstruction · KITTI-360 static scenesdepth error: 0.892 -> 0.872Improved
add ground loss L_ground (ablation)HUGSIM ground model · nuScenes groundKID extrapolated: 0.249 -> 0.196Improved
add ground loss L_ground (ablation)HUGSIM ground model · nuScenes groundPSNR interpolated: 28.03 -> 27.44Hurt
make Gaussian scale sx,sz learnable (ablation)HUGSIM ground model · nuScenes groundPSNR: 25.84 -> 27.44Improved
make Gaussian position learnable (ablation)HUGSIM ground model · nuScenes groundKID extrapolated: 0.242 -> 0.196Improved
normalize semantic softmax in 3D instead of 2D (ablation)HUGSIM semantics · KITTI-360 3D semanticsaverage mIoU class: 0.402 -> 0.505Improved

Later papers that compared with this method

1 later accepted paper reports HUGSIM 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 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