SuPrNet: Super Proxy for 4D occupancy forecasting

A Liang, W Chen, J Fang, H Zhao - Knowledge-Based Systems, 2024 - Elsevier
Spacetime (4D) occupancy forecasting explicitly models the future development of self-
driving vehicles (SDVs) themselves and their surrounding environment, which is highly …

TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception

R Chen, H Park, B Zhang, W Shao, P Luo… - arXiv preprint arXiv …, 2024 - arxiv.org
Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent
unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR …

DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes

H Bian, L Kong, H Xie, L Pan, Y Qiao, Z Liu - arXiv preprint arXiv …, 2024 - arxiv.org
LiDAR scene generation has been developing rapidly recently. However, existing methods
primarily focus on generating static and single-frame scenes, overlooking the inherently …

LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation

C Zhou, L Fu, S Peng, Y Yan, Z Zhang, Y Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving
scenarios. Recent approaches utilize neural radiance fields combined with the physical …

GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields

W Xue, Z Zheng, F Lu, H Wei, G Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Although recent efforts have extended Neural Radiance Fields (NeRF) into LiDAR point
cloud synthesis, the majority of existing works exhibit a strong dependence on precomputed …

SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving

G Hess, C Lindström, M Fatemi, C Petersson… - arXiv preprint arXiv …, 2024 - arxiv.org
Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive
testing across diverse driving scenarios. Simulation is a key ingredient for conducting such …

Generative LiDAR Editing with Controllable Novel Object Layouts

SH Ho, B Thach, M Zhu - arXiv preprint arXiv:2412.00592, 2024 - arxiv.org
We propose a framework to edit real-world Lidar scans with novel object layouts while
preserving a realistic background environment. Compared to the synthetic data generation …

LiDAR-GS: Real-time LiDAR Re-Simulation using Gaussian Splatting

Q Chen, S Yang, S Du, T Tang, P Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
LiDAR simulation plays a crucial role in closed-loop simulation for autonomous driving.
Although recent advancements, such as the use of reconstructed mesh and Neural …

Application of foundation models for autonomous driving: a survey of data synthesis

S Gao, B Gao, P Wei, J Guo, M Yuan… - … Conference on Traffic …, 2024 - spiedigitallibrary.org
With the evolution of data-driven autonomous driving technology, transferring driving
responsibility from humans to machines is now feasible. Addressing the long-tail distribution …

DYNAMICCITY: LARGE-SCALE OCCUPANCY GENERATION FROM DYNAMIC SCENES

TG Generation - openreview.net
LiDAR scene generation has been developing rapidly recently. However, existing methods
primarily focus on generating static and single-frame scenes, overlooking the inherently …