# CNN-based synthesis of realistic high-resolution LiDAR data

arXiv: https://arxiv.org/abs/1907.00787 · HTML: https://mlsanity.com/paper/1907.00787/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [TULIP: Transformer for Upsampling of LiDAR Point Clouds](https://mlsanity.com/paper/2312.06733/) (2023)
- [A Realism Metric for Generated LiDAR Point Clouds](https://mlsanity.com/paper/2208.14958/) (2022)
- [HALS: A Height-Aware Lidar Super-Resolution Framework for Autonomous Driving](https://mlsanity.com/paper/2202.03901/) (2022)
- [Quantifying point cloud realism through adversarially learned latent representations](https://mlsanity.com/paper/2109.11775/) (2021)
- [LitS: A novel Neighborhood Descriptor for Point Clouds](https://mlsanity.com/paper/2602.04838/) (2026)
- [A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving](https://mlsanity.com/paper/2602.15904/) (2026)

## Abstract (arXiv)

This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our generated output with real-world sensor data by applying a perceptual loss. In large-scale experiments on real-world datasets, we evaluate both the geometric accuracy and semantic segmentation performance using our generated data vs. ground truth. In a mean opinion score testing we further assess the perceptual quality of our generated point clouds. Our results demonstrate a significant quantitative and qualitative improvement in both geometry and semantics over traditional non CNN-based up-sampling methods.