An Experimental Study of SOTA LiDAR Segmentation Models

• URL: http://arxiv.org/abs/2502.12860v1
• Date: Tue, 18 Feb 2025 13:48:22 GMT
• Title: An Experimental Study of SOTA LiDAR Segmentation Models
• Abstract summary: Point cloud segmentation (PCS) is to classify each point in point clouds.<n>PCS models can be roughly divided into point-, voxel-, and range image-based models.<n>No work has been found to report comprehensive comparisons among the state-of-the-art point-, voxel-, and range image-based models.
• Score: 3.8056056756169316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud segmentation (PCS) is to classify each point in point clouds. The task enables robots to parse their 3D surroundings and run autonomously. According to different point cloud representations, existing PCS models can be roughly divided into point-, voxel-, and range image-based models. However, no work has been found to report comprehensive comparisons among the state-of-the-art point-, voxel-, and range image-based models from an application perspective, bringing difficulty in utilizing these models for real-world scenarios. In this paper, we provide thorough comparisons among the models by considering the LiDAR data motion compensation and the metrics of model parameters, max GPU memory allocated during testing, inference latency, frames per second, intersection-over-union (IoU) and mean IoU (mIoU) scores. The experimental results benefit engineers when choosing a reasonable PCS model for an application and inspire researchers in the PCS field to design more practical models for a real-world scenario.

Related papers

• Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition [55.13619415776905]
  This paper explores the use of publicly available models and civilian datasets to achieve reasonable performance in military contexts.<n>We benchmark several state-of-the-art models, including six iterations of the YOLO series and two variations on the DETR framework.<n>We compare the performance of the models using mAP@0.5 and mAP@0.5:0.95, across A2G and Ground-to-Ground (G2G) perspective, target size and model size.
  arXiv  Detail & Related papers  (2026-08-18T15:43:34Z)
• Towards Compact Autonomous Driving Perception with Balanced Learning and Multi-sensor Fusion [5.557543974847597]
  We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass.<n>The model performs multiple views of semantic segmentation, depth estimation, light detection and ranging (LiDAR) segmentation, and bird's eye view projection simultaneously.
  arXiv  Detail & Related papers  (2026-06-02T00:35:42Z)
• PC2Model: ISPRS benchmark on 3D point cloud to model registration [1.0775419935941009]
  This paper introduces the PC2Model benchmark, a dataset designed to support the training and evaluation of both classical and data-driven methods.<n>Simulated data provide precise ground truth and controlled conditions, while real-world data introduce sensor and environmental artefacts.<n>This design supports robust training and evaluation across domains and enables the systematic analysis of model transferability from simulated to real-world scenarios.
  arXiv  Detail & Related papers  (2026-04-21T15:44:40Z)
• Point Cloud Segmentation of Agricultural Vehicles using 3D Gaussian Splatting [12.323236593352698]
  This work aims to introduce a novel pipeline for generating realistic synthetic data.<n>We generate 3D assets of multiple agricultural vehicles instead of using generic models.<n>We evaluate the impact of synthetic data on segmentation models such as PointNet++, Point Transformer V3, and OACNN, by training and validating the models only on synthetic data.
  arXiv  Detail & Related papers  (2025-06-05T13:19:27Z)
• Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solution [1.8029479474051309]
  We design a hybrid edge-cloud solution that leverages the efficiency of smaller models for local processing while deferring to larger, more accurate cloud-based models when necessary. Specifically, we propose a novel unsupervised data generation method, Dual-Model Distillation (DMD), to train a lightweight switcher model that can predict when the edge model's output is uncertain. Experimental results on the action classification task show that our framework not only requires less computational overhead, but also improves accuracy compared to using a large model alone.
  arXiv  Detail & Related papers  (2024-10-16T02:06:27Z)
• ED-ViT: Splitting Vision Transformer for Distributed Inference on Edge Devices [13.533267828812455]
  We propose a novel Vision Transformer splitting framework, ED-ViT, to execute complex models across multiple edge devices efficiently. Specifically, we partition Vision Transformer models into several sub-models, where each sub-model is tailored to handle a specific subset of data classes. We conduct extensive experiments on five datasets with three model structures, demonstrating that our approach significantly reduces inference latency on edge devices.
  arXiv  Detail & Related papers  (2024-10-15T14:38:14Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling [20.784555362703294]
  We establish a public benchmark dataset for car-following behavior modeling. The benchmark consists of more than 80K car-following events extracted from five public driving datasets. Results show that the deep deterministic policy gradient (DDPG) based model performs competitively with a lower MSE for spacing.
  arXiv  Detail & Related papers  (2023-05-25T08:59:26Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• p$^3$VAE: a physics-integrated generative model. Application to the pixel-wise classification of airborne hyperspectral images [0.6849746341453253]
  We introduce p$3$VAE, a generative model that integrates a physical model. We apply p$3$VAE to the pixel-wise classification of airborne hyperspectral images.
  arXiv  Detail & Related papers  (2022-10-19T09:32:15Z)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Conditional Generation of Synthetic Geospatial Images from Pixel-level and Feature-level Inputs [0.0]
  We present a conditional generative model, called VAE-Info-cGAN, for synthesizing semantically rich images simultaneously conditioned on a pixel-level condition (PLC) and a feature-level condition (FLC) The proposed model can accurately generate various forms of macroscopic aggregates across different geographic locations while conditioned only on atemporal representation of the road network.
  arXiv  Detail & Related papers  (2021-09-11T06:58:19Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• Discrete Point Flow Networks for Efficient Point Cloud Generation [36.03093265136374]
  Generative models have proven effective at modeling 3D shapes and their statistical variations. We introduce a latent variable model that builds on normalizing flows to generate 3D point clouds of an arbitrary size. For single-view shape reconstruction we also obtain results on par with state-of-the-art voxel, point cloud, and mesh-based methods.
  arXiv  Detail & Related papers  (2020-07-20T14:48:00Z)

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.