LiT: Unifying LiDAR "Languages" with LiDAR Translator

Yixing Lao, Tao Tang, Xiaoyang Wu, Peng Chen, Kaicheng Yu, Hengshuang Zhao

Keywords: LiDAR Translation, Domain Unification, 3D Detection

TL;DR: LiT, the LiDAR Translator, directly translates point clouds across domains, unifying diverse LiDAR datasets to support scalable cross-domain and multi-domain learning for autonomous driving.

Abstract: LiDAR data exhibits significant domain gaps due to variations in sensors, vehicles, and driving environments, creating “language barriers” that limit the effective use of data across domains and the scalability of LiDAR perception models. To address these challenges, we introduce the LiDAR Translator (LiT), a framework that directly translates LiDAR data across domains, enabling both cross-domain adaptation and multi-domain joint learning. LiT integrates three key components: a scene modeling module for precise foreground and background reconstruction, a LiDAR modeling module that models LiDAR rays statistically and simulates ray-drop, and a fast, hardware-accelerated ray casting engine. LiT enables state-of-the-art zero-shot and unified domain detection across diverse LiDAR datasets, marking a step toward data-driven domain unification for autonomous driving systems. Source code and demos are available at: https://yxlao.github.io/lit.

Primary Area: Machine vision

Submission Number: 4652