arXiv cs.AI· NVIDIA, :, Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang, Seung Wook Kim, Ning Xu, Qi Wu, Janick Martinez Esturo, Shengyu Huang, Nick Schneider, Laura Leal-Taixe, Zan Gojcic, Sanja Fidler·· 3 小时前AI 评分51
NVIDIA 发布 Instant NuRec：前馈式 3D 高斯重建加速驾驶场景仿真
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
AI 导读
NVIDIA 团队在 arXiv 发布 Instant NuRec，一种前馈神经重建模型，可将短时多视角驾驶日志经单次前向推理转为可仿真的 3D 高斯泼溅（3DGS）世界。
正文 · 原文
Authors:NVIDIA: Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang, Seung Wook Kim, Ning Xu, Qi Wu, Janick Martinez Esturo, Shengyu Huang, Nick Schneider, Laura Leal-Taixe, Zan Gojcic, Sanja Fidler
Abstract:3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent years, neural simulation has become predominant, with methods such as NuRec playing a central role; however, these methods remain relatively slow and typically require per-scene tuning. In this work, we present Instant NuRec, a feed-forward neural reconstruction model that turns a short multi-view driving log into a fully simulatable 3D Gaussian Splatting (3DGS) world in a single forward pass. The model accepts multi-view input from a calibrated camera rig and emits a layered output consisting of static and dynamic 3DGS layers, a sky cubemap, and per-camera ISP corrections, while providing native support for non-pinhole camera models via 3DGUT. It reconstructs a 10-20-second multi-camera scene in roughly 1.5 seconds and achieves a PSNR on the Waymo Open Dataset that is 2.01 dB above the strongest evaluated baseline. Instant NuRec is deeply integrated into NuRec and is compatible with AlpaSim for closed-loop simulation.
| Comments: | Project Page: this https URL |
| Subjects: | Graphics (cs.GR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.14203 [cs.GR] |
| (or arXiv:2607.14203v2 [cs.GR] for this version) | |
| https://doi.org/10.48550/arXiv.2607.14203 arXiv-issued DOI via DataCite |
Submission history
From: Jiahui Huang [view email]
[v1]
Wed, 15 Jul 2026 17:50:23 UTC (3,469 KB)
[v2]
Wed, 11 Nov 2026 00:06:51 UTC (1,991 KB)
来源：arXiv cs.AI · arxiv.org