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

• URL: http://arxiv.org/abs/2511.20065v1
• Date: Tue, 25 Nov 2025 08:37:49 GMT
• Title: FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds
• Authors: Xiaoge Zhang, Zijie Wu, Mingtao Feng, Zichen Geng, Mehwish Nasim, Saeed Anwar, Ajmal Mian,
• Abstract summary: FLaTEC is a frequency-aware compression model that enables the compression of a full scan with high compression ratios.<n>We convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements.<n>Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both datasets.
• Score: 52.997038111673966
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization [24.710418261668888]
  We present S-PRESSO, a 48kHz sound effect compression model that produces both continuous and discrete embeddings at ultra-lows.<n>Our model relies on a pretrained latent diffusion model to decode compressed audio embeddings learned by a latent encoder.<n>We demonstrate that S-PRESSO outperforms both continuous and discrete baselines in audio quality, acoustic similarity and reconstruction metrics.
  arXiv  Detail & Related papers  (2026-02-16T10:28:38Z)
• KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding [72.12756830560217]
  Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.<n>Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value cache during inference has emerged as a primary efficiency bottleneck.<n>By down-sampling the Key-Value vector dimensions into a latent space, we can significantly reduce the KV Cache footprint and improve inference speed.
  arXiv  Detail & Related papers  (2025-07-15T12:52:12Z)
• Single-step Diffusion for Image Compression at Ultra-Low Bitrates [19.76457078979179]
  We propose a single-step diffusion model for image compression that delivers high perceptual quality and fast decoding at ultra-lows.<n>Our approach incorporates two key innovations: (i) Vector-Quantized Residual (VQ-Residual) training, which factorizes a structural base code and a learned residual in latent space.<n>Ours achieves comparable compression performance to state-of-the-art methods while improving decoding speed by about 50x.
  arXiv  Detail & Related papers  (2025-06-19T19:53:27Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• High-Frequency Enhanced Hybrid Neural Representation for Video Compression [32.38933743785333]
  This paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network.<n>Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network.<n> Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods.
  arXiv  Detail & Related papers  (2024-11-11T03:04:46Z)
• Fast Feedforward 3D Gaussian Splatting Compression [55.149325473447384]
  3D Gaussian Splatting (FCGS) is an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass.<n>FCGS achieves a compression ratio of over 20X while maintaining fidelity, surpassing most per-scene SOTA optimization-based methods.
  arXiv  Detail & Related papers  (2024-10-10T15:13:08Z)
• High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusion [4.76749587454871]
  We propose an efficient Uncertainty-Guided image compression approach with wavelet Diffusion (UGDiff)<n>Our approach focuses on high frequency compression via the wavelet transform, since high frequency components are crucial for reconstructing image details.<n> Comprehensive experiments on two benchmark datasets validate the effectiveness of UGDiff.
  arXiv  Detail & Related papers  (2024-07-17T13:21:31Z)
• Lossy Compression with Gaussian Diffusion [28.930398810600504]
  We describe a novel lossy compression approach called DiffC which is based on unconditional diffusion generative models. We implement a proof of concept and find that it works surprisingly well despite the lack of an encoder transform. We show that a flow-based reconstruction achieves a 3 dB gain over ancestral sampling at highs.
  arXiv  Detail & Related papers  (2022-06-17T16:46:31Z)
• Inception Transformer [151.939077819196]
  Inception Transformer, or iFormer, learns comprehensive features with both high- and low-frequency information in visual data. We benchmark the iFormer on a series of vision tasks, and showcase that it achieves impressive performance on image classification, COCO detection and ADE20K segmentation.
  arXiv  Detail & Related papers  (2022-05-25T17:59:54Z)
• LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network [14.848279912686948]
  Recent learning-based image compression methods do not consider the performance drop in the high-frequency region. We propose a new method that proceeds the encoding in a coarse-to-fine manner to separate and process low and high-frequency regions differently. Experiments show that the proposed method achieves state-of-the-art performance for benchmark high-resolution datasets.
  arXiv  Detail & Related papers  (2021-12-13T04:49:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.