LiteViLNet: Lightweight Vision-LiDAR Fusion Network for Efficient Road Segmentation

• URL: http://arxiv.org/abs/2605.21007v1
• Date: Wed, 20 May 2026 10:44:06 GMT
• Title: LiteViLNet: Lightweight Vision-LiDAR Fusion Network for Efficient Road Segmentation
• Abstract summary: We propose textbfLiteViLNet, a lightweight multi-modal network that fuses RGB texture information and LiDAR geometric information for efficient road segmentation.<n> Specifically, we design a dual-stream lightweight encoder and depth-wise separable convolutions to extract hierarchical features from both modalities with minimal parameters.<n>Experiments on the KITTI Road dataset and real-world applications demonstrate that LiteViLNet achieves a promising balance between accuracy and efficiency.
• Score: 6.81209407358202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time inference, especially for deployment on resource-constrained edge devices. Existing multi-modal road segmentation methods often rely on heavy transformer-based encoders to achieve state-of-the-art performance, but their enormous computational cost prohibits real-time deployment on embedded platforms. To address this dilemma, we propose \textbf{LiteViLNet}, a lightweight multi-modal network that fuses RGB texture information and LiDAR geometric information for efficient road segmentation. Specifically, we design a dual-stream lightweight encoder and depth-wise separable convolutions to extract hierarchical features from both modalities with minimal parameters. We further propose a Multi-Scale Feature Fusion Module (MSFM) to facilitate cross-modal interaction at different levels, and a large-kernel-bridge module to capture long-range dependencies with linear complexity. Extensive experiments on the KITTI Road dataset and real-world applications demonstrate that LiteViLNet achieves a promising balance between accuracy and efficiency. Notably, with only 14.04M parameters, our model attains a 96.36\% MaxF score, ranking the best among all CNN-based methods and being comparable to larger transformer-based models, and runs at 163.79 FPS in model-only inference on RTX 4060 Ti (22.18 FPS on Jetson Orin NX). It outperforms numerous heavy-weight methods in inference speed while maintaining highly competitive accuracy, fully validating the potential of LiteViLNet for real-time embedded deployment in autonomous driving and intelligent robotics.

Related papers

• CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation [6.478456907626643]
  Cross-Layer Independent Deformable Description (CLIDD) is a method that achieves superior distinctiveness by sampling directly from independent feature hierarchies.<n>To ensure real-time performance, we implement a hardware-aware kernel fusion strategy.<n>We develop a scalable framework that integrates lightweight architectures with a training protocol.
  arXiv  Detail & Related papers  (2026-01-14T07:03:01Z)
• Low-Level Matters: An Efficient Hybrid Architecture for Robust Multi-frame Infrared Small Target Detection [5.048364655933007]
  Multi-frame infrared small target detection plays a crucial role in low-altitude and maritime surveillance.<n>The hybrid architecture combining CNNs and Transformers shows great promise for enhancing multi-frame IRSTD.<n>We propose LVNet, a simple yet powerful hybrid architecture that redefines low-level feature learning hybrid frameworks.
  arXiv  Detail & Related papers  (2025-03-04T02:53:25Z)
• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking.<n>DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget.<n>Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving [2.1204495827342438]
  TwinLiteNet+ is an enhanced multi-task segmentation model for real-time drivable area and lane segmentation.<n>It employs a hybrid encoder architecture that integrates stride-based dilated convolutions and depthwise separable dilated convolutions.<n>The model is available in four configurations, ranging from the ultra-compact TwinLiteNet+_Nano (34K parameters) to the high-performance TwinLiteNet+_Large (1.94M parameters)
  arXiv  Detail & Related papers  (2024-03-25T17:17:45Z)
• AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation [4.54656749337919]
  AsymFormer is a novel network that improves real-time semantic segmentation accuracy using RGB-D multi-modal information. AsymFormer uses an asymmetrical backbone for multimodal feature extraction, reducing redundant parameters. AsymFormer can strike a balance between high accuracy and efficiency.
  arXiv  Detail & Related papers  (2023-09-25T11:57:16Z)
• Parameter-efficient Tuning of Large-scale Multimodal Foundation Model [68.24510810095802]
  We propose A graceful prompt framework for cross-modal transfer (Aurora) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0.1M trainable parameters to implement the multimodal prompt tuning. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach.
  arXiv  Detail & Related papers  (2023-05-15T06:40:56Z)
• Efficient Context Integration through Factorized Pyramidal Learning for Ultra-Lightweight Semantic Segmentation [1.0499611180329804]
  We propose a novel Factorized Pyramidal Learning (FPL) module to aggregate rich contextual information in an efficient manner. We decompose the spatial pyramid into two stages which enables a simple and efficient feature fusion within the module to solve the notorious checkerboard effect. Based on the FPL module and FIR unit, we propose an ultra-lightweight real-time network, called FPLNet, which achieves state-of-the-art accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-02-23T05:34:51Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• 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)
• Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform [62.91011959772665]
  Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles. Current approaches that operate directly on the point cloud use complex spatial aggregation operations. We propose a projection-based method, called Multi-scale Interaction Network (MINet), which is very efficient and accurate.
  arXiv  Detail & Related papers  (2020-08-20T19:06:11Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.