LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision

TL;DR

LiDAR-EVS is a novel framework that significantly improves the realism and robustness of extrapolated-view LiDAR synthesis for autonomous driving, enabling better simulation along unseen trajectories without requiring multi-pass data.

Contribution

It introduces a plug-and-play framework with pseudo-LiDAR supervision and spatial dropout regularization to enhance extrapolated-view LiDAR synthesis in autonomous driving.

Findings

Achieves state-of-the-art results on three datasets.

Demonstrates robustness to diverse trajectory variations.

Enables reliable LiDAR simulation for unseen driving paths.

Abstract

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time LiDAR and camera synthesis in autonomous driving simulation. However, simulating LiDAR with 3DGS remains challenging for extrapolated views beyond the training trajectory, as existing methods are typically trained on single-traversal sensor scans, suffer from severe overfitting and poor generalization to novel ego-vehicle paths. To enable reliable simulation of LiDAR along unseen driving trajectories without external multi-pass data, we present LiDAR-EVS, a lightweight framework for robust extrapolated-view LiDAR simulation in autonomous driving. Designed to be plug-and-play, LiDAR-EVS readily extends to diverse LiDAR sensors and neural rendering baselines with minimal modification. Our framework comprises two key components: (1) pseudo extrapolated-view point cloud supervision with multi-frame LiDAR fusion, view transformation, occlusion curling, and intensity adjustment; (2) spatially-constrained dropout regularization that promotes robustness to diverse trajectory variations encountered in real-world driving. Extensive experiments demonstrate that LiDAR-EVS achieves SOTA performance on extrapolated-view LiDAR synthesis across three datasets, making it a promising tool for data-driven simulation, closed-loop evaluation, and synthetic data generation in autonomous driving systems.