arXiv cs.AI· Kevin David Hayes, Alex Hanson, Allen Tu, Pranav Asthana, Matthias Zwicker, Tom Goldstein·· 3 小时前AI 评分35
RIDE-Splat：面向真实驾驶环境的挡风玻璃反射去除与 3D 重建方法
RIDE-Splat: Reflection Removal for In-the-Wild Driving Environments
AI 导读
RIDE-Splat 是一个从带位姿的驾驶视频中做无反射 3D 重建的 pipeline，无需干净图像、反射掩码或预训练网络。它将透过挡风玻璃的世界一致性透射内容分配给 3DGS 场景，把主导的相机附着反射建模为一张共享的有符号 RGB 图像，推理时丢弃该反射图像。
正文 · 原文
Abstract:Driving video captured through a windshield violates the world-space consistency assumed by 3D Gaussian Splatting (3DGS): the road scene exhibits parallax while cabin reflections remain attached to the camera, causing standard 3DGS to embed reflected content into the reconstructed scene. We introduce RIDE-Splat, a pipeline for reflection-free 3D reconstruction from posed driving video without clean images, reflection masks, or pretrained networks. RIDE-Splat assigns world-consistent transmission through the windshield to a 3DGS scene and the dominant camera-attached reflection to one shared, signed RGB image. It builds the clean reconstruction in two passes. First, it learns the 3D geometry and the signed reflection image, representing both added radiance and transmission attenuation. Then, it uses the reflection-removed training images to fit a clean 3DGS model. At inference, the reflection image is discarded, preserving the standard 3DGS rendering path. We also introduce the RIDE-Splat Dataset, the first 3D reconstruction benchmark for reflection removal from driving video -- with real driving scenes, physical windshield reflections in training views, and separately captured non-reflective evaluation images. Across the RIDE-Splat Dataset, XLD, and Wayve, RIDE-Splat outperforms 3DGS, DC-Gaussian, and RobustSplat on all nine aggregate metrics, improving PSNR by up to 3.59 dB and reducing LPIPS by up to 0.0876. We achieve the highest metrics in 38 out of 42 per-scene comparisons and removes windshield reflections that remain visible in the baselines while preserving the transmitted scene.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34632 [cs.CV] |
| (or arXiv:2610.34632v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34632 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kevin Hayes [view email]
[v1]
Sun, 25 Oct 2026 23:11:47 UTC (4,078 KB)
来源：arXiv cs.AI · arxiv.org