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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add box optimization with the unicycle model instead of noisy boxes (ablation) | HUGSIM dynamic reconstruction · KITTI (5% noise) | PSNR: 23.83 -> 28.78 | Improved |
| add unicycle model to per-frame box optimization (ablation) | HUGSIM dynamic reconstruction · KITTI (5% noise) | PSNR: 24.80 -> 28.78 | Improved |
| add unicycle model to per-frame box optimization (ablation) | HUGSIM dynamic reconstruction · KITTI (20% noise) | translation error: 0.612 -> 0.176 | Improved |
| add naive per-frame box optimization without unicycle model (ablation) | HUGSIM dynamic reconstruction · KITTI (5% noise) | translation error: 0.027 -> 0.051 | Hurt |
| add affine exposure transform (ablation) | HUGSIM static reconstruction · KITTI-360 static scenes | PSNR: 24.18 -> 24.52 | Improved |
| add semantic loss L_S (ablation) | HUGSIM static reconstruction · KITTI-360 static scenes | PSNR: 24.47 -> 24.52 | No clear effect |
| add semantic loss L_S (ablation) | HUGSIM static reconstruction · KITTI-360 static scenes | depth error: 0.892 -> 0.872 | Improved |
| add ground loss L_ground (ablation) | HUGSIM ground model · nuScenes ground | KID extrapolated: 0.249 -> 0.196 | Improved |
| add ground loss L_ground (ablation) | HUGSIM ground model · nuScenes ground | PSNR interpolated: 28.03 -> 27.44 | Hurt |
| make Gaussian scale sx,sz learnable (ablation) | HUGSIM ground model · nuScenes ground | PSNR: 25.84 -> 27.44 | Improved |
| make Gaussian position learnable (ablation) | HUGSIM ground model · nuScenes ground | KID extrapolated: 0.242 -> 0.196 | Improved |
| normalize semantic softmax in 3D instead of 2D (ablation) | HUGSIM semantics · KITTI-360 3D semantics | average mIoU class: 0.402 -> 0.505 | Improved |
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.
- DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing (ECCV 2026 · better on 3 of 3 shared results)
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.
- NeuRAD — NeuRAD: Neural Rendering for Autonomous Driving (CVPR 2024) · better on 2 of 3 shared results
- mip-NeRF — Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 2021) · better on 1 of 1 shared result
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
- NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking (NeurIPS 2024 · similarity 0.89)
- DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation (CVPR 2025 · similarity 0.88)
- SceneCrafter: Controllable Multi-View Driving Scene Editing (CVPR 2025 · similarity 0.86)
- ReSim: Reliable World Simulation for Autonomous Driving (NeurIPS 2025 · similarity 0.86)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.86)
- VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.86)
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.
