Year: 2024
Type: conference-paper
Abstract: LiDAR data generation has seen significant advancements and success in recent years, particularly in applications such as autonomous driving and robotics.However, existing generative models often struggle with poor foreground object quality due to two main reasons: (1) foreground objects typically occupy a small portion of the 3D point cloud in a frame; and (2) objects of the same class often exhibit large intra-class variances.To address these challenges, we propose a variant of the Denoising Diffusion Probabilistic Model (DDPM) and introduce an object focal loss to increase emphasis on foreground objects during training, particularly those with less frequent appearances.The proposed focal diffusion process is able to enhance the distinctiveness of foreground objects in the generated lidar frames.Experiments on the public KITTI-360 dataset showed that the proposed focal diffusion process outperformed existing generation approaches, establishing a new state-of-the-art in 3D LiDAR generation.Ablation studies further validated the superiority of the proposed object focal loss.
Authors: Huijie Zhang, Xiaobai Liu
Institution: San Diego State University
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
Funder: National Science Foundation
OpenAlex ID: W4405868539