NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction

2026-09-29

AI Summary

This study addresses the absence of intensity data in LiDAR simulation and the high computational cost and poor reusability of conventional per-scene optimization. We propose a feedforward LiDAR intensity generation framework that integrates pseudo-near-infrared conversion with hierarchical intrinsic decomposition, alongside geometry-aware modulation and source-domain distribution calibration, to synthesize dense intensity maps directly from RGB and geometric inputs. Crucially, the method achieves cross-scene generalization using fixed weights, eliminating the need for target-scene labels or gradient-based fitting. Experiments demonstrate that our framework surpasses existing baselines in accuracy and fidelity on the Waymo and nuScenes datasets. Furthermore, its practical utility has been validated through downstream SLAM tasks implemented within the Unreal Engine 5 environment.

Abstract

LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it or reproduce it using reconstruction methods that require real intensity supervision and per-scene optimization. These requirements increase data-collection and fitting costs and limit reuse across simulated scenes. We present NIDAR, a feed-forward framework that synthesizes dense intensity-like observations from RGB appearance and simulator geometry. NIDAR combines pretrained pseudo-NIR translation, hierarchical intrinsic decomposition, geometry-aware modulation, and source-domain distribution calibration to transfer reflectance-related image cues to simulated point clouds. Its learned components are trained offline using Waymo data; their weights and calibration remain fixed during evaluation on Waymo and nuScenes. Deployment therefore requires neither target-scene intensity labels nor target-scene gradient-based fitting. The reported comparisons show competitive pixel-wise accuracy and favorable structural and perceptual fidelity against the evaluated reconstruction baselines. A controlled pseudo-NIR-versus-RGB diagnostic further shows that the pseudo-NIR prior is most beneficial when used through the paper-aligned reflectance-and-remapping route, rather than as a simple direct intensity regressor. We further integrate NIDAR with Unreal Engine 5, Isaac Sim, and a generative LiDAR pipeline. Two intensity-aware SLAM systems evaluated in two simulated indoor scenes suggest potential downstream utility, but do not constitute real-robot validation. NIDAR therefore offers a scalable intensity-synthesis interface for the evaluated settings; cross-wavelength, camera-configuration, embedded, and real-sensor validation remain future work.

Problem

• LiDAR intensity reconstruction
• simulation pipelines
• per-scene optimization
• scene-agnostic
• intensity supervision

Innovation

• LiDAR intensity reconstruction
• intrinsic decomposition
• pseudo-NIR translation
• scene-agnostic
• feed-forward framework