Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes

• URL: http://arxiv.org/abs/2404.13550v1
• Date: Sun, 21 Apr 2024 06:31:29 GMT
• Title: Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
• Authors: Kang You, Kai Liu, Li Yu, Pan Gao, Dandan Ding,
• Abstract summary: Pointsoup is an efficient learning-based geometry that attains high-performance and extremely low-decoding-latency simultaneously. It offers variable-rate control with a single neural model (2.9MB), which is attractive for industrial practitioners.
• Score: 15.262269044326915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a crucial requirement in real-world application. In this paper, we propose Pointsoup, an efficient learning-based geometry codec that attains high-performance and extremely low-decoding-latency simultaneously. Inspired by conventional Trisoup codec, a point model-based strategy is devised to characterize local surfaces. Specifically, skin features are embedded from local windows via an attention-based encoder, and dilated windows are introduced as cross-scale priors to infer the distribution of quantized features in parallel. During decoding, features undergo fast refinement, followed by a folding-based point generator that reconstructs point coordinates with fairly fast speed. Experiments show that Pointsoup achieves state-of-the-art performance on multiple benchmarks with significantly lower decoding complexity, i.e., up to 90$\sim$160$\times$ faster than the G-PCCv23 Trisoup decoder on a comparatively low-end platform (e.g., one RTX 2080Ti). Furthermore, it offers variable-rate control with a single neural model (2.9MB), which is attractive for industrial practitioners.

Related papers

• High Efficiency Wiener Filter-based Point Cloud Quality Enhancement for MPEG G-PCC [23.8642501868336]
  Point clouds directly record the geometry and attributes of scenes or objects by a large number of points. geometry-based point cloud compression (G-PCC) standard for both static and dynamic point clouds. We propose a high efficiency Wiener filter that can be integrated into the encoder and decoder pipeline of G-PCC.
  arXiv  Detail & Related papers  (2025-03-21T18:24:58Z)
• High-Efficiency Neural Video Compression via Hierarchical Predictive Learning [27.41398149573729]
  Enhanced Deep Hierarchical Video Compression-DHVC 2.0- introduces superior compression performance and impressive complexity efficiency. Uses hierarchical predictive coding to transform each video frame into multiscale representations. Supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss.
  arXiv  Detail & Related papers  (2024-10-03T15:40:58Z)
• SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds [51.313922535437726]
  We propose an end-to-end compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy model.
  arXiv  Detail & Related papers  (2024-09-16T13:59:43Z)
• Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement [19.575833741231953]
  We use the KNN method to determine the neighborhoods of raw surface points. A conditional probability model is adaptive to local geometry, leading to significant rate reduction. We incorporate an implicit neural representation into the refinement layer, allowing the decoder to sample points on the underlying surface at arbitrary densities.
  arXiv  Detail & Related papers  (2024-08-06T05:24:06Z)
• Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression [39.052583172727324]
  The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds. This paper proposes a hierarchical prior-based super resolution method for point cloud geometry compression.
  arXiv  Detail & Related papers  (2024-02-17T11:15:38Z)
• StarNet: Style-Aware 3D Point Cloud Generation [82.30389817015877]
  StarNet is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network. Our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-03-28T08:21:44Z)
• DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets [95.84755169585492]
  We present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks.
  arXiv  Detail & Related papers  (2023-01-15T09:31:58Z)
• IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression [11.410441760314564]
  We propose a set of significant improvements to patch-based point cloud compression. Experiments show that the improved patch-based autoencoder outperforms the state-of-the-art in terms of rate-distortion performance.
  arXiv  Detail & Related papers  (2022-08-04T08:12:35Z)
• SoftPool++: An Encoder-Decoder Network for Point Cloud Completion [93.54286830844134]
  We propose a novel convolutional operator for the task of point cloud completion. The proposed operator does not require any max-pooling or voxelization operation. We show that our approach achieves state-of-the-art performance in shape completion at low and high resolutions.
  arXiv  Detail & Related papers  (2022-05-08T15:31:36Z)
• ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization [71.91942002659795]
  We investigate and adapt network quantization techniques to accelerate inference and enable its use on compute limited platforms. ZippyPoint, our efficient quantized network with binary descriptors, improves the network runtime speed, the descriptor matching speed, and the 3D model size. These improvements come at a minor performance degradation as evaluated on the tasks of homography estimation, visual localization, and map-free visual relocalization.
  arXiv  Detail & Related papers  (2022-03-07T18:59:03Z)
• HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation [95.47168925127089]
  We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. We design a new type of hypernetwork, composed of a nested U-Net for drawing higher level context features.
  arXiv  Detail & Related papers  (2020-12-21T18:58:18Z)
• Multiscale Point Cloud Geometry Compression [29.605320327889142]
  We propose a multiscale-to-end learning framework which hierarchically reconstructs the 3D Point Cloud Geometry. The framework is developed on top of a sparse convolution based autoencoder for point cloud compression and reconstruction.
  arXiv  Detail & Related papers  (2020-11-07T16:11:16Z)

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.