Papers
arxiv:2508.03690

Veila: Panoramic LiDAR Generation from a Monocular RGB Image

Published on Aug 5
Authors:
,
,
,
,
,
,
,
,
,

Abstract

A conditional diffusion framework, Veila, enhances panoramic LiDAR data generation using monocular RGB images by addressing spatial control, alignment, and coherence challenges with novel mechanisms and metrics.

AI-generated summary

Realistic and controllable panoramic LiDAR data generation is critical for scalable 3D perception in autonomous driving and robotics. Existing methods either perform unconditional generation with poor controllability or adopt text-guided synthesis, which lacks fine-grained spatial control. Leveraging a monocular RGB image as a spatial control signal offers a scalable and low-cost alternative, which remains an open problem. However, it faces three core challenges: (i) semantic and depth cues from RGB are vary spatially, complicating reliable conditioning generation; (ii) modality gaps between RGB appearance and LiDAR geometry amplify alignment errors under noisy diffusion; and (iii) maintaining structural coherence between monocular RGB and panoramic LiDAR is challenging, particularly in non-overlap regions between images and LiDAR. To address these challenges, we propose Veila, a novel conditional diffusion framework that integrates: a Confidence-Aware Conditioning Mechanism (CACM) that strengthens RGB conditioning by adaptively balancing semantic and depth cues according to their local reliability; a Geometric Cross-Modal Alignment (GCMA) for robust RGB-LiDAR alignment under noisy diffusion; and a Panoramic Feature Coherence (PFC) for enforcing global structural consistency across monocular RGB and panoramic LiDAR. Additionally, we introduce two metrics, Cross-Modal Semantic Consistency and Cross-Modal Depth Consistency, to evaluate alignment quality across modalities. Experiments on nuScenes, SemanticKITTI, and our proposed KITTI-Weather benchmark demonstrate that Veila achieves state-of-the-art generation fidelity and cross-modal consistency, while enabling generative data augmentation that improves downstream LiDAR semantic segmentation.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.03690 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.03690 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.03690 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.