SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.04004 · CVPR · 2025

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

Ziwei Liu, Liang Pan, Xiang Xu, Lingdong Kong, Hui Shuai, Qingshan Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focus on sparse voxel representation, overlooking the complementary attributes provided by other LiDAR representations. In this work, we propose LiMoE, a framework that integrates the Mixture of Experts (MoE) paradigm into LiDAR data representation learning to synergistically combine multiple representations, such as range images, sparse voxels, and raw points. Our approach consists of three stages: i) Image-to-LiDAR Pretraining, which transfers prior knowledge from images to point clouds across different representations; ii) Contrastive Mixture Learning (CML), which uses MoE to adaptively activate relevant attributes from each representation and distills these mixed features into a unified 3D network; iii) Semantic Mixture Supervision (SMS), which combines semantic logits from multiple representations to boost downstream segmentation performance. Extensive experiments across eleven largescale LiDAR datasets demonstrate our effectiveness and superiority. The code has been made publicly accessible.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.04004")
get_code_for_paper("2501.04004")
have("2501.04004")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2501.04004.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2501.04004.svg)](https://syntology.ai/paper/2501.04004)

Connect an agent — have() is free.