1.5秒生成可模拟的3D驾驶场景，比基线高2.01dB
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
- 单次前向传播完成多视角输入到3DGS世界的重建
- 10-20秒场景重建耗时约1.5秒，Waymo数据集上PSNR领先2.01dB
- 支持非针孔相机与闭环仿真，适合自动驾驶研发
3D仿真平台对自动驾驶至关重要，可实现端到端策略评估，降低开发成本并提升安全性。近年来神经仿真成为主流，如NuRec方法占据核心地位；但这些方法仍较慢，且通常需针对每个场景调参。本文提出Instant NuRec，一种前馈式神经重建模型，能将一段多视角驾驶日志在一次前向传播中转化为可完全模拟的3D高斯点云（3DGS）世界。该模型接收校准相机阵列的多视角输入，输出包含静态与动态3DGS层、天空立方体贴图及每相机ISP校正的分层结果，并通过3DGUT原生支持非针孔相机模型。可在约1.5秒内重建10-20秒的多相机场景，在Waymo Open Dataset上达到比最强基线高出2.01 dB的PSNR。Instant NuRec深度集成于NuRec，兼容AlpaSim用于闭环仿真。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。