通过潜空间跨模态对齐与翻译的 LiDAR 到 4D 雷达扩散桥
LiDAR-to-4DRadar Diffusion Bridge via Cross-Modal Alignment and Translation in Latent Space
把扩散桥（diffusion bridge）用在两个已对齐的潜空间之间做跨模态翻译，可迁移到 LiDAR→相机、深度→RGB 等「缺失模态补全」任务；其 patch-wise 对比对齐 + key-voxel-aware VAE 的组合，为高维稠密张量（雷达/体素）的生成式数据增强提供了可复用范式。
原文依据 we formulate the translation as a diffusion bridge process between LiDAR and radar latents
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论毫米波雷达的全天候能力使其在自动驾驶感知中日益重要。然而，雷达数据采集成本高昂，催生了通过数据生成来扩充雷达数据集的需求。现有工作主要针对部分雷达表示（如 2D 或 3D 切片），导致信息损失并限制了下游性能。为克服这些问题，我们引入了 LiDAR 到 4D 雷达翻译这一新任务：在保持空间与语义一致性的 LiDAR 数据引导下，生成包含三个空间轴与一个多普勒轴的完整 4D 雷达张量。我们提出了一种在对齐的 LiDAR-4DRadar 潜空间中运行的新型扩散桥模型 L2RLDB 来完成该任务。具体而言，首先，一个关键体素感知的变分自编码器将高维、含噪的雷达张量压缩到紧凑的潜变量空间，同时实现精确的数值重建与关键体素识别。其次，为弥合稀疏 3D LiDAR 与稠密 4D 雷达之间的跨模态鸿沟，我们设计了一个逐块对比学习模块，在语义与空间上对齐 LiDAR 潜变量与雷达潜变量。最后，我们将该翻译建模为 LiDAR 潜变量与雷达潜变量之间的扩散桥过程，从而能够从缺乏多普勒信息的 LiDAR 输入合成完整的雷达张量。实验验证 L2RLDB 实现了高保真的 4D 雷达生成，并通过数据增强显著提升了下游检测性能。
英文原文摘要 1444 字符
Millimeter-wave radar's all-weather capability makes it increasingly vital for autonomous perception. However, the high cost of radar data collection drives the need for data generation to augment radar datasets. Existing works mainly target partial radar representations, e.g., 2D or 3D slices, leading to information loss and limited downstream performance. To overcome these issues, we introduce the novel task of LiDAR-to-4DRadar translation, which generates complete 4D radar tensors, with three spatial and one Doppler axes, guided by LiDAR data that preserve spatial and semantic consistency. We propose a novel diffusion bridge model in an aligned LiDAR-4DRadar latent space, namely L2RLDB, to tackle this task. Specifically, first, a key-voxel-aware VAE compresses high-dimensional, noisy radar tensors into a compact latent space, while enabling precise numerical reconstruction and key-voxel identification. Second, to bridge the cross-modal gap between sparse 3D LiDAR and dense 4D radar, we develop a patch-wise contrastive learning module to align LiDAR latents with radar semantically and spatially. Finally, we formulate the translation as a diffusion bridge process between LiDAR and radar latents, enabling the synthesis of full radar tensors from Doppler-lacking LiDAR inputs. Experiments verify that L2RLDB achieves high-fidelity 4D radar generation and significantly improves downstream detection through data augmentation.