研究人员开发了两个新的真实LiDAR场景生成框架，以解决当前文本到LiDAR生成能力的局限性。T2LDM++利用自条件表示引导机制来改进对象细节和可控性，并在超过100,000个文本-LiDAR样本上进行了训练。另一方面，LaGen是第一个专为逐帧、交互式LiDAR场景生成设计的自回归框架，能够使用边界框信息生成高保真4D场景，并减轻长序列中的误差累积。 AI
影响 这些进展可以显著改进自动驾驶系统的数据增强和模拟。
排序理由 两篇介绍LiDAR场景生成新模型的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.30147v1 Announce Type: new Abstract: Recent progress in Text-to-Image generation benefits from large-scale Text-Image pairs. However, the scarcity of Text-LiDAR pairs often causes over-smoothed scenes and limited controllability. In this paper, we rethink the limitatio…
arXiv:2511.21256v2 Announce Type: replace Abstract: Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety-critical scenario evaluation. Unlike the widely studied image modality, in this…
Recent progress in Text-to-Image generation benefits from large-scale Text-Image pairs. However, the scarcity of Text-LiDAR pairs often causes over-smoothed scenes and limited controllability. In this paper, we rethink the limitations of Text-LiDAR generation task, focusing on al…