Spectral-Geometric Neural Fields for Pose-Free LiDAR View Synthesis

TL;DR

This paper introduces SG-NLF, a pose-free LiDAR neural radiance field framework that combines spectral priors and geometric consistency to improve view synthesis quality without relying on camera poses.

Contribution

We propose a novel pose-free LiDAR NeRF method integrating spectral information, geometric consistency, and adversarial learning to enhance reconstruction and pose accuracy.

Findings

Improves reconstruction quality by over 35.8%.

Enhances pose accuracy by over 68.8%.

Effective in low-frequency scenarios.

Abstract

Neural Radiance Fields (NeRF) have shown remarkable success in image novel view synthesis (NVS), inspiring extensions to LiDAR NVS. However, most methods heavily rely on accurate camera poses for scene reconstruction. The sparsity and textureless nature of LiDAR data also present distinct challenges, leading to geometric holes and discontinuous surfaces. To address these issues, we propose SG-NLF, a pose-free LiDAR NeRF framework that integrates spectral information with geometric consistency. Specifically, we design a hybrid representation based on spectral priors to reconstruct smooth geometry. For pose optimization, we construct a confidence-aware graph based on feature compatibility to achieve global alignment. In addition, an adversarial learning strategy is introduced to enforce cross-frame consistency, thereby enhancing reconstruction quality. Comprehensive experiments demonstrate the effectiveness of our framework, especially in challenging low-frequency scenarios. Compared to previous state-of-the-art methods, SG-NLF improves reconstruction quality and pose accuracy by over 35.8% and 68.8%. Our work can provide a novel perspective for LiDAR view synthesis.