DrivePTS：一种渐进学习框架，结合文本与结构增强用于驾驶场景生成
DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation
提出渐进学习策略与互信息约束解耦几何条件，并利用视觉语言模型生成多视角分层描述作为细粒度文本引导，结合频域结构损失增强前景细节，可迁移至其他条件生成任务。
原文依据 a frequency-guided structure loss is introduced to strengthen the model's sensitivity to high-frequency elements
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论合成多样化的驾驶场景是验证自动驾驶系统鲁棒性和泛化能力的关键数据增强技术。当前方法将高清地图和3D边界框作为几何条件聚合到扩散模型中，用于条件场景生成。然而，隐式的条件间依赖关系导致当控制条件独立变化时生成失败。此外，这些方法在语义和结构方面细节不足。具体而言，简短且视角不变的描述限制了语义上下文，导致背景建模薄弱。同时，采用均匀空间加权的标准去噪损失忽略了前景结构细节，造成视觉失真和模糊。为解决这些挑战，我们提出DrivePTS，包含三项关键创新。首先，我们的框架采用渐进学习策略，并辅以显式的互信息约束，以缓解几何条件间的依赖关系。其次，利用视觉语言模型生成跨六个语义方面的多视角分层描述，提供细粒度的文本引导。第三，引入频率引导的结构损失，增强模型对高频元素的敏感性，提高前景结构保真度。大量实验表明，DrivePTS在生成多样化驾驶场景方面实现了最优的保真度和可控性。值得注意的是，DrivePTS成功生成了先前方法失败的罕见场景，突显了其强大的泛化能力。
英文原文摘要 1677 字符
Synthesis of diverse driving scenes serves as a crucial data augmentation technique for validating the robustness and generalizability of autonomous driving systems. Current methods aggregate high-definition (HD) maps and 3D bounding boxes as geometric conditions in diffusion models for conditional scene generation. However, implicit inter-condition dependency causes generation failures when control conditions change independently. Additionally, these methods suffer from insufficient details in both semantic and structural aspects. Specifically, brief and view-invariant captions restrict semantic contexts, resulting in weak background modeling. Meanwhile, the standard denoising loss with uniform spatial weighting neglects foreground structural details, causing visual distortions and blurriness. To address these challenges, we propose DrivePTS, which incorporates three key innovations. Firstly, our framework adopts a progressive learning strategy to mitigate inter-dependency between geometric conditions, reinforced by an explicit mutual information constraint. Secondly, a Vision-Language Model is utilized to generate multi-view hierarchical descriptions across six semantic aspects, providing fine-grained textual guidance. Thirdly, a frequency-guided structure loss is introduced to strengthen the model's sensitivity to high-frequency elements, improving foreground structural fidelity. Extensive experiments demonstrate that our DrivePTS achieves state-of-the-art fidelity and controllability in generating diverse driving scenes. Notably, DrivePTS successfully generates rare scenes where prior methods fail, highlighting its strong generalization ability.