# Real-Time LiDAR Super-Resolution via Frequency-Aware Multi-Scale Fusion

arXiv: https://arxiv.org/abs/2511.07377 · HTML: https://mlsanity.com/paper/2511.07377/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Global Filter Networks for Image Classification](https://mlsanity.com/paper/2107.00645/) (2021)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review](https://mlsanity.com/paper/2005.09830/) (2020)
- [Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems](https://mlsanity.com/paper/2004.08467/) (2020)
- [Learning Spatial Fusion for Single-Shot Object Detection](https://mlsanity.com/paper/1911.09516/) (2019)
- [Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion](https://mlsanity.com/paper/2403.13470/) (2024)
- [Simulation-based Lidar Super-resolution for Ground Vehicles](https://mlsanity.com/paper/2004.05242/) (2020)
- [Implicit LiDAR Network: LiDAR Super-Resolution via Interpolation Weight Prediction](https://mlsanity.com/paper/2203.06413/) (2022)
- [LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection](https://mlsanity.com/paper/2301.12515/) (2023)
- [TULIP: Transformer for Upsampling of LiDAR Point Clouds](https://mlsanity.com/paper/2312.06733/) (2023)
- [SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds](https://mlsanity.com/paper/2505.10601/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving](https://mlsanity.com/paper/2602.15904/) (2026)

## Abstract (arXiv)

LiDAR super-resolution addresses the challenge of achieving high-quality 3D perception from cost-effective, low-resolution sensors. While recent transformer-based approaches like TULIP show promise, they remain limited to spatial-domain processing with restricted receptive fields. We introduce FLASH (Frequency-aware LiDAR Adaptive Super-resolution with Hierarchical fusion), a novel framework that overcomes these limitations through dual-domain processing. FLASH integrates two key innovations: (i) Frequency-Aware Window Attention that combines local spatial attention with global frequency-domain analysis via FFT, capturing both fine-grained geometry and periodic scanning patterns at log-linear complexity. (ii) Adaptive Multi-Scale Fusion that replaces conventional skip connections with learned position-specific feature aggregation, enhanced by CBAM attention for dynamic feature selection. Extensive experiments on KITTI demonstrate that FLASH achieves state-of-the-art performance across all evaluation metrics, surpassing even uncertainty-enhanced baselines that require multiple forward passes. Notably, FLASH outperforms TULIP with Monte Carlo Dropout while maintaining single-pass efficiency, which enables real-time deployment. The consistent superiority across all distance ranges validates that our dual-domain approach effectively handles uncertainty through architectural design rather than computationally expensive stochastic inference, making it practical for autonomous systems.