# FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2511.20065 · HTML: https://mlsanity.com/paper/2511.20065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Frequency-Aware Transformer for Learned Image Compression](https://mlsanity.com/paper/2310.16387/) (2023)
- [Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning](https://mlsanity.com/paper/2402.02500/) (2024)
- [MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models](https://mlsanity.com/paper/2011.07590/) (2020)
- [Density-preserving Deep Point Cloud Compression](https://mlsanity.com/paper/2204.12684/) (2022)
- [Learning-based lossless compression of 3D point cloud geometry](https://mlsanity.com/paper/2011.14700/) (2020)
- [Make-A-Shape: a Ten-Million-scale 3D Shape Model](https://mlsanity.com/paper/2401.11067/) (2024)
- [Multiscale deep context modeling for lossless point cloud geometry compression](https://mlsanity.com/paper/2104.09859/) (2021)
- [BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios](https://mlsanity.com/paper/2212.05758/) (2022)
- [RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2503.12382/) (2025)
- [Point Cloud Compression with Sibling Context and Surface Priors](https://mlsanity.com/paper/2205.00760/) (2022)
- [R-PCC: A Baseline for Range Image-based Point Cloud Compression](https://mlsanity.com/paper/2109.07717/) (2021)
- [Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression](https://mlsanity.com/paper/2209.12512/) (2022)
- [Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes](https://mlsanity.com/paper/2404.13550/) (2024)
- [Variable Rate Compression for Raw 3D Point Clouds](https://mlsanity.com/paper/2202.13862/) (2022)

## Abstract (arXiv)

Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-frequency and high-frequency components contribute differently at the same resolution. To address this, we propose FLaTEC, a frequency-aware compression model that enables the compression of a full scan with high compression ratios. Our approach introduces a frequency-aware mechanism that decouples low-frequency structures and high-frequency textures, while hybridizing latent triplanes as a compact proxy for point cloud. Specifically, we convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements. We then devise a frequency-disentangling technique that extracts compact low-frequency content while collecting high-frequency details across scales. The decoupled low-frequency and high-frequency components are stored in binary format. During decoding, full-spectrum signals are progressively recovered via a modulation block. Additionally, to compensate for the loss of 3D correlation, we introduce an efficient frequency-based attention mechanism that fosters local connectivity and outputs arbitrary resolution points. Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both SemanticKITTI and Ford datasets.