# Implicit LiDAR Network: LiDAR Super-Resolution via Interpolation Weight Prediction

arXiv: https://arxiv.org/abs/2203.06413 · HTML: https://mlsanity.com/paper/2203.06413/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2022.

## Built on by (most cited first, 14 of 14)

- [LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.09256/) (2023)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [TULIP: Transformer for Upsampling of LiDAR Point Clouds](https://mlsanity.com/paper/2312.06733/) (2023)
- [Lidar Upsampling with Sliced Wasserstein Distance](https://mlsanity.com/paper/2301.13558/) (2023)
- [SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds](https://mlsanity.com/paper/2505.10601/) (2025)
- [Fast LiDAR Upsampling using Conditional Diffusion Models](https://mlsanity.com/paper/2405.04889/) (2024)
- [PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit Surface](https://mlsanity.com/paper/2310.08755/) (2023)
- [Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive scene Segmentation](https://mlsanity.com/paper/2509.01317/) (2025)
- [Real-Time LiDAR Super-Resolution via Frequency-Aware Multi-Scale Fusion](https://mlsanity.com/paper/2511.07377/) (2025)
- [WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Research](https://mlsanity.com/paper/2402.19059/) (2024)
- [Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping](https://mlsanity.com/paper/2407.15554/) (2024)
- [ALICE-LRI: A General Method for Lossless Range Image Generation for Spinning LiDAR Sensors without Calibration Metadata](https://mlsanity.com/paper/2510.20708/) (2025)
- [A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving](https://mlsanity.com/paper/2602.15904/) (2026)
- [Fast and Accurate Outlier-Aware LiDAR Super-Resolution for SLAM Applications](https://mlsanity.com/paper/2606.28607/) (2026)

## Abstract (arXiv)

Super-resolution of LiDAR range images is crucial to improving many downstream tasks such as object detection, recognition, and tracking. While deep learning has made a remarkable advances in super-resolution techniques, typical convolutional architectures limit upscaling factors to specific output resolutions in training. Recent work has shown that a continuous representation of an image and learning its implicit function enable almost limitless upscaling. However, the detailed approach, predicting values (depths) for neighbor pixels in the input and then linearly interpolating them, does not best fit the LiDAR range images since it does not fill the unmeasured details but creates a new image with regression in a high-dimensional space. In addition, the linear interpolation blurs sharp edges providing important boundary information of objects in 3-D points. To handle these problems, we propose a novel network, Implicit LiDAR Network (ILN), which learns not the values per pixels but weights in the interpolation so that the superresolution can be done by blending the input pixel depths but with non-linear weights. Also, the weights can be considered as attentions from the query to the neighbor pixels, and thus an attention module in the recent Transformer architecture can be leveraged. Our experiments with a novel large-scale synthetic dataset demonstrate that the proposed network reconstructs more accurately than the state-of-the-art methods, achieving much faster convergence in training.