English

Learned Multimodal Compression for Autonomous Driving

Image and Video Processing 2024-08-16 v1 Computer Vision and Pattern Recognition

Abstract

Autonomous driving sensors generate an enormous amount of data. In this paper, we explore learned multimodal compression for autonomous driving, specifically targeted at 3D object detection. We focus on camera and LiDAR modalities and explore several coding approaches. One approach involves joint coding of fused modalities, while others involve coding one modality first, followed by conditional coding of the other modality. We evaluate the performance of these coding schemes on the nuScenes dataset. Our experimental results indicate that joint coding of fused modalities yields better results compared to the alternatives.

Keywords

Cite

@article{arxiv.2408.08211,
  title  = {Learned Multimodal Compression for Autonomous Driving},
  author = {Hadi Hadizadeh and Ivan V. Bajić},
  journal= {arXiv preprint arXiv:2408.08211},
  year   = {2024}
}

Comments

6 pages, 5 figures, IEEE MMSP 2024

R2 v1 2026-06-28T18:13:53.380Z