GA-Drive：用于自由视角驾驶场景生成的几何-外观解耦建模
GA-Drive: Geometry-Appearance Decoupled Modeling for Free-viewpoint Driving Scene Generation
AI总结：
GA-Drive通过几何-外观解耦和扩散生成技术，生成可编辑的高保真驾驶场景，提升自动驾驶训练和评估的效率与效果。
摘要：
自由视角、可编辑且高保真的驾驶模拟器对训练和评估端到端自动驾驶系统至关重要。本文提出GA-Drive，一种新型模拟框架，能够通过几何-外观解耦和基于扩散的生成技术，生成用户指定的新型轨迹的相机视角。给定沿记录轨迹拍摄的一组图像及对应的场景几何信息，GA-Drive利用几何信息生成伪视角，然后通过训练的视频扩散模型将其转换为逼真视角。这种方式实现了场景几何与外观的解耦。这种解耦的优势在于支持通过最先进的视频到视频编辑技术进行外观编辑，同时保持底层几何结构，从而在原始和新型轨迹上实现一致的编辑。大量实验表明，GA-Drive在NTA-IoU、NTL-IoU和FID分数方面显著优于现有方法。
英文摘要：
A free-viewpoint, editable, and high-fidelity driving simulator is crucial for training and evaluating end-to-end autonomous driving systems. In this paper, we present GA-Drive, a novel simulation framework capable of generating camera views along user-specified novel trajectories through Geometry-Appearance Decoupling and Diffusion-Based Generation. Given a set of images captured along a recorded trajectory and the corresponding scene geometry, GA-Drive synthesizes novel pseudo-views using geometry information. These pseudo-views are then transformed into photorealistic views using a trained video diffusion model. In this way, we decouple the geometry and appearance of scenes. An advantage of such decoupling is its support for appearance editing via state-of-the-art video-to-video editing techniques, while preserving the underlying geometry, enabling consistent edits across both original and novel trajectories. Extensive experiments demonstrate that GA-Drive substantially outperforms existing methods in terms of NTA-IoU, NTL-IoU, and FID scores.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
