PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge

• URL: http://arxiv.org/abs/2506.00438v1
• Date: Sat, 31 May 2025 07:34:54 GMT
• Title: PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge
• Authors: Keisuke Sugiura, Mizuki Yasuda, Hiroki Matsutani,
• Abstract summary: We introduce a parameter-efficient architecture for point cloud feature extraction based on a continuous stack of blocks with residual connections.<n>PointODE shows competitive accuracy to the state-of-the-art models on both synthetic and real-world datasets.
• Score: 0.8403582577557918
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embedded edge devices are often used as a computing platform to run real-world point cloud applications, but recent deep learning-based methods may not fit on such devices due to limited resources. In this paper, we aim to fill this gap by introducing PointODE, a parameter-efficient ResNet-like architecture for point cloud feature extraction based on a stack of MLP blocks with residual connections. We leverage Neural ODE (Ordinary Differential Equation), a continuous-depth version of ResNet originally developed for modeling the dynamics of continuous-time systems, to compress PointODE by reusing the same parameters across MLP blocks. The point-wise normalization is proposed for PointODE to handle the non-uniform distribution of feature points. We introduce PointODE-Elite as a lightweight version with 0.58M trainable parameters and design its dedicated accelerator for embedded FPGAs. The accelerator consists of a four-stage pipeline to parallelize the feature extraction for multiple points and stores the entire parameters on-chip to eliminate most of the off-chip data transfers. Compared to the ARM Cortex-A53 CPU, the accelerator implemented on a Xilinx ZCU104 board speeds up the feature extraction by 4.9x, leading to 3.7x faster inference and 3.5x better energy-efficiency. Despite the simple architecture, PointODE-Elite shows competitive accuracy to the state-of-the-art models on both synthetic and real-world classification datasets, greatly improving the trade-off between accuracy and inference cost.

Related papers

• FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems [51.15230303652732]
  FLEX (F Low EXpert) is a backbone architecture for generative modeling of-temporal physical systems.<n>It reduces the variance of the velocity field in the diffusion model, which helps stabilize training.<n>It achieves accurate predictions for super-resolution and forecasting tasks using as few features as two reverse diffusion steps.
  arXiv  Detail & Related papers  (2025-05-23T00:07:59Z)
• Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers [1.19658449368018]
  This paper proposes a novel PEFT algorithm called Side Token Adaptation on a neighborhood Graph (STAG) to achieve superior temporal and spatial efficiency.<n>STAG employs a graph convolutional side network operating in parallel with a frozen backbone Transformer to adapt tokens to downstream tasks.<n>We also present Point Cloud Classification 13 (PCC13), a new benchmark comprising diverse publicly available 3D point cloud datasets.
  arXiv  Detail & Related papers  (2025-02-19T22:58:56Z)
• Efficient Spatio-Temporal Signal Recognition on Edge Devices Using PointLCA-Net [0.0]
  This paper presents an approach that combines PointNet's feature extraction with the in-memory computing capabilities and energy efficiency of neuromorphic systems fortemporal signal recognition.<n>PointNet achieves high accuracy and significantly lower energy burden during both inference and training than comparable approaches.
  arXiv  Detail & Related papers  (2024-11-21T20:48:40Z)
• Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction [8.598010350935596]
  This paper systematically evaluates a deep learning reconstruction framework.<n>We design a hybrid loss function combining weighted mean squared with error structural similarity index.<n>We enhance the model's capability to capture cross-modaltemporal correlations and energy-displacement nonlinearities.
  arXiv  Detail & Related papers  (2024-10-08T11:49:18Z)
• TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Cameras [5.925545594655497]
  Event cameras generate sparse and asynchronous data, which is incompatible with the traditional frame-based method. We propose a point cloud network called TTPOINT which achieves results even compared to the state-of-the-art (SOTA) frame-based method in action recognition tasks.
  arXiv  Detail & Related papers  (2023-08-19T11:58:31Z)
• 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)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)
• DeepCompress: Efficient Point Cloud Geometry Compression [1.808877001896346]
  We propose a more efficient deep learning-based encoder architecture for point clouds compression. We show that incorporating the learned activation function from Efficient Neural Image Compression (CENIC) yields dramatic gains in efficiency and performance. Our proposed modifications outperform the baseline approaches by a small margin in terms of Bjontegard delta rate and PSNR values.
  arXiv  Detail & Related papers  (2021-06-02T23:18:11Z)
• Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels [52.60092598312894]
  We propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. Our proposed solution results in minimal energy consumption and $CO$ emission compared to the considered baselines.
  arXiv  Detail & Related papers  (2021-06-02T07:36:27Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

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.