A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)

• URL: http://arxiv.org/abs/2404.01568v4
• Date: Sun, 30 Jun 2024 20:40:24 GMT
• Title: A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
• Authors: Dehao Yuan, Cornelia Fermüller, Tahseen Rabbani, Furong Huang, Yiannis Aloimonos,
• Abstract summary: We propose VecKM, a local point cloud geometry encoder that is descriptive and efficient to compute. VecKM constructs the local geometry encoding using all neighboring points, producing a more descriptive encoding. VecKM is efficient to compute and scalable to large point cloud inputs.
• Score: 37.87282737463472
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose VecKM, a local point cloud geometry encoder that is descriptive and efficient to compute. VecKM leverages a unique approach by vectorizing a kernel mixture to represent the local point cloud. Such representation's descriptiveness is supported by two theorems that validate its ability to reconstruct and preserve the similarity of the local shape. Unlike existing encoders downsampling the local point cloud, VecKM constructs the local geometry encoding using all neighboring points, producing a more descriptive encoding. Moreover, VecKM is efficient to compute and scalable to large point cloud inputs: VecKM reduces the memory cost from $(n^2+nKd)$ to $(nd+np)$; and reduces the major runtime cost from computing $nK$ MLPs to $n$ MLPs, where $n$ is the size of the point cloud, $K$ is the neighborhood size, $d$ is the encoding dimension, and $p$ is a marginal factor. The efficiency is due to VecKM's unique factorizable property that eliminates the need of explicitly grouping points into neighbors. In the normal estimation task, VecKM demonstrates not only 100x faster inference speed but also highest accuracy and strongest robustness. In classification and segmentation tasks, integrating VecKM as a preprocessing module achieves consistently better performance than the PointNet, PointNet++, and point transformer baselines, and runs consistently faster by up to 10 times.

Related papers

• IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means [20.13045791225961]
  We propose an implicit, differentiable $k$-means algorithm (IDKM) which eliminates the major memory restriction of DKM. We show that IDKM achieves comparable performance to DKM with less compute time and less memory. We also use IDKM and IDKM-JFB to quantize a large neural network, Resnet18, on hardware where DKM cannot train at all.
  arXiv  Detail & Related papers  (2023-12-12T22:02:57Z)
• Do you know what q-means? [50.045011844765185]
  Clustering is one of the most important tools for analysis of large datasets. We present an improved version of the "$q$-means" algorithm for clustering. We also present a "dequantized" algorithm for $varepsilon which runs in $Obig(frack2varepsilon2(sqrtkd + log(Nd))big.
  arXiv  Detail & Related papers  (2023-08-18T17:52:12Z)
• SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers [76.13755422671822]
  This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework. We introduce a novel Attention-to-Mask (atm) module to design a lightweight decoder effective for plain ViT. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5%$ of the computational cost.
  arXiv  Detail & Related papers  (2023-06-09T22:29:56Z)
• FInC Flow: Fast and Invertible $k \times k$ Convolutions for Normalizing Flows [2.156373334386171]
  Invertible convolutions have been an essential element for building expressive normalizing flow-based generative models. We propose a $k times k$ convolutional layer and Deep Normalizing Flow architecture.
  arXiv  Detail & Related papers  (2023-01-23T04:31:03Z)
• Rapid Person Re-Identification via Sub-space Consistency Regularization [51.76876061721556]
  Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation. We propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25$ times.
  arXiv  Detail & Related papers  (2022-07-13T02:44:05Z)
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework [55.40001810884942]
  We introduce a pure residual network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark.
  arXiv  Detail & Related papers  (2022-02-15T01:39:07Z)
• Distribution Compression in Near-linear Time [27.18971095426405]
  We introduce Compress++, a simple meta-procedure for speeding up any thinning algorithm. It delivers $sqrtn$ points with $mathcalO(sqrtlog n/n)$ integration error and better-than-Monte-Carlo maximum mean discrepancy.
  arXiv  Detail & Related papers  (2021-11-15T17:42:57Z)
• FriendlyCore: Practical Differentially Private Aggregation [67.04951703461657]
  We propose a simple and practical tool $mathsfFriendlyCore$ that takes a set of points $cal D$ from an unrestricted (pseudo) metric space as input. When $cal D$ has effective diameter $r$, $mathsfFriendlyCore$ returns a "stable" subset $cal D_Gsubseteq cal D$ that includes all points. $mathsfFriendlyCore$ can be used to preprocess the input before privately aggregating it, potentially simplifying the aggregation or boosting its accuracy
  arXiv  Detail & Related papers  (2021-10-19T17:43:50Z)
• Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation [7.557684072809662]
  We present a novel lightweight convolutional neural network for point cloud analysis. Our method operates on the entire point sets without sampling and achieves good performances efficiently.
  arXiv  Detail & Related papers  (2021-09-23T19:39:01Z)
• Exact Acceleration of K-Means++ and K-Means$\|$ [22.66983713481359]
  K-Means++ and K-Means$|$ have become de facto tools for selecting the initial seeds of K-means. We develop specialized triangle inequality pruning strategies and a dynamic priority queue to show the first acceleration of K-Means++ and K-Means$|$.
  arXiv  Detail & Related papers  (2021-05-06T20:22:55Z)

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.