LiT: Unifying LiDAR "Languages" with LiDAR Translator

Yixing Lao, Tao Tang, Xiaoyang Wu, Peng Chen, Kaicheng Yu +1 more
1/1/2024

No official code found. Best implementation: yxlao/lit (25 stars, Apache-2.0, last commit 2025-01-14).

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

DOISemantic Scholar

Code Implementations(1)

yxlao/litCommunity72%
Apache-2.0

(NeurIPS 2024) LiT: Unifying LiDAR "Languages" with LiDAR Translator

251C, C++Dec 11, 20241 years agoApache-2.0

Similar Papers

DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception

84% match1 repo322023

Training-Free Model Merging for Multi-target Domain Adaptation

83% match2 repos182024

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds

83% match2023

High-Fidelity Digital Twins for Bridging the Sim2Real Gap in LiDAR-Based ITS Perception

83% match2025

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

83% match2024

DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding

83% match2 repos862025

Cite this paper

@article{lao2024lit,
  title  = {LiT: Unifying LiDAR "Languages" with LiDAR Translator},
  author = {Yixing Lao and Tao Tang and Xiaoyang Wu and Peng Chen and Kaicheng Yu and Hengshuang Zhao},
  year   = {2024},
  doi    = {10.52202/079017-2973},
  url    = {https://doi.org/10.52202/079017-2973},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/21aad3c1a21f96aaa4679ba35551540bfdaa2922.svg)](https://codeofpaper.com/paper/21aad3c1a21f96aaa4679ba35551540bfdaa2922)

Discussion