Table of Contents
HIMap Framework Overview
Comparison of experimental results
Home Technology peripherals AI Better than all methods! HIMap: End-to-end vectorized HD map construction

Better than all methods! HIMap: End-to-end vectorized HD map construction

Mar 19, 2024 pm 03:00 PM
frame map

Vectorized high-definition (HD) map construction requires predicting the categories and point coordinates of map elements (such as road boundaries, lane dividers, crosswalks, etc.). State-of-the-art methods are mainly based on point-level representation learning for regressing precise point coordinates. However, this pipeline has limitations in obtaining element-level information and handling element-level failures, such as wrong element shapes or entanglements between elements. In order to solve the above problems, this paper proposes a simple and effective HybrId framework, named HIMap, to fully learn and interact with point-level and element-level information.

Specifically, a hybrid representation called HIQuery is introduced to represent all map elements, and a point element interactor is proposed to interactively extract hybrid information of elements, such as point location and element shape and encode it into HIQuery. In addition, point-element consistency constraints are also proposed to enhance the consistency between point-level and element-level information. Finally, the output point elements of the integrated HIQuery can be directly converted into the class, point coordinates and mask of the map element. Extensive experiments are conducted on nuScenes and Argoverse2 datasets, showing consistently superior results to previous methods. It is worth noting that the method achieves 77.8mAP on the nuScenes dataset, which is significantly better than the previous SOTA by at least 8.3mAP!

Paper name: HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction

Paper link: https://arxiv.org/pdf/2403.08639.pdf

HIMap first introduces a hybrid representation called HIQuery to represent all map elements in the map. It is a set of learnable parameters that can be iteratively updated and refined by interacting with BEV features. Then, a multi-layer hybrid decoder is designed to encode the hybrid information of map elements (such as point position, element shape) into HIQuery and perform point element interaction, see Figure 2. Each layer of the hybrid decoder includes point element interactors, self-attention and FFN. Inside the point-element interactor, a mutual interaction mechanism is implemented to realize the exchange of point-level and element-level information and avoid the learning bias of single-level information. Finally, integrated HIQuery's output point elements can be directly converted to the element's point coordinates, class, and mask. In addition, point-element consistency constraints are also proposed to enhance the consistency between point-level and element-level information.

Better than all methods! HIMap: End-to-end vectorized HD map construction

HIMap Framework Overview

The overall process of HIMap is shown in Figure 3(a). HIMap is compatible with a variety of airborne sensor data, such as RGB images from multi-view cameras, point clouds from lidar, or multi-modal data. Here we take multi-view RGB images as an example to explain how HIMap works.

Better than all methods! HIMap: End-to-end vectorized HD map construction

BEV Feature Extractor is a tool for extracting BEV features from multi-view RGB images. Its core includes extracting the backbone part of multi-scale 2D features from each perspective, obtaining the FPN part of single-scale features by fusing and refining multi-scale features, and utilizing the 2D to BEV feature conversion module to map 2D features into BEV features. . This process helps convert image information into BEV features more suitable for processing and analysis, improving the usability and accuracy of features. Through this method, we can better understand and utilize the information in multi-view images, providing stronger support for subsequent data processing and decision-making.

HIQuery: In order to fully learn the point-level and element-level information of map elements, HIQuery is introduced to represent all elements in the map!

Hybrid decoder: The hybrid decoder produces integrated HIQuery by iteratively interacting HIQuery Qh with BEV features X.

The goal of the point element interactor is to interactively extract point-level and element-level information of map elements and encode it into HIQuery. The motivation for the interaction of the two levels of information comes from their complementarity. Point-level information contains local location knowledge, while element-level information provides global shape and semantic knowledge. This interaction thus enables mutual refinement of local and global information of map elements.

Considering the original difference between point-level representation and element-level representation, which focus on local information and overall information respectively, the learning of two-level representations may also interfere with each other. This will increase the difficulty of information interaction and reduce the effectiveness of information interaction. Therefore, point element consistency constraints are introduced to enhance the consistency between each point level and element level information, and the discriminability of elements can also be enhanced!

Comparison of experimental results

The paper conducted experiments on NuScenes Dataset and Argoverse2 Dataset!

Comparison of SOTA model on nuScenes val-set:

Better than all methods! HIMap: End-to-end vectorized HD map construction

Comparison of SOTA model on Argoverse2 val set:

Better than all methods! HIMap: End-to-end vectorized HD map construction

Comparison with SOTA model under nuScenes validation set multi-modal data:

Better than all methods! HIMap: End-to-end vectorized HD map construction

Better than all methods! HIMap: End-to-end vectorized HD map construction

More ablation experiments:

Better than all methods! HIMap: End-to-end vectorized HD map construction

Better than all methods! HIMap: End-to-end vectorized HD map construction

Better than all methods! HIMap: End-to-end vectorized HD map construction

The above is the detailed content of Better than all methods! HIMap: End-to-end vectorized HD map construction. For more information, please follow other related articles on the PHP Chinese website!

Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
2 weeks ago By 尊渡假赌尊渡假赌尊渡假赌
Hello Kitty Island Adventure: How To Get Giant Seeds
1 months ago By 尊渡假赌尊渡假赌尊渡假赌
Two Point Museum: All Exhibits And Where To Find Them
1 months ago By 尊渡假赌尊渡假赌尊渡假赌

Hot Tools

Notepad++7.3.1

Notepad++7.3.1

Easy-to-use and free code editor

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

Zend Studio 13.0.1

Zend Studio 13.0.1

Powerful PHP integrated development environment

Dreamweaver CS6

Dreamweaver CS6

Visual web development tools

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

How to evaluate the cost-effectiveness of commercial support for Java frameworks How to evaluate the cost-effectiveness of commercial support for Java frameworks Jun 05, 2024 pm 05:25 PM

Evaluating the cost/performance of commercial support for a Java framework involves the following steps: Determine the required level of assurance and service level agreement (SLA) guarantees. The experience and expertise of the research support team. Consider additional services such as upgrades, troubleshooting, and performance optimization. Weigh business support costs against risk mitigation and increased efficiency.

How to use at-a-glance directions on Google Maps How to use at-a-glance directions on Google Maps Jun 13, 2024 pm 09:40 PM

A year after its launch, Google Maps has launched a new feature. Once you set a route to your destination on the map, it summarizes your travel route. Once your journey begins, you can "Browse" route guidance from your phone's lock screen. You can use Google Maps to see your estimated arrival time and route. Throughout your trip, you can view navigation information on your lock screen, and by unlocking your phone, you can view navigation information without accessing Google Maps. By unlocking your phone, you can view navigation information without accessing Google Maps. By unlocking your phone, you can view navigation information without accessing Google Maps. By unlocking your phone, you can view navigation information without accessing Google Maps. By unlocking your phone, you can view navigation information without accessing Google Maps. By unlocking your phone, you can view navigation information without accessing Google Maps.

How do the lightweight options of PHP frameworks affect application performance? How do the lightweight options of PHP frameworks affect application performance? Jun 06, 2024 am 10:53 AM

The lightweight PHP framework improves application performance through small size and low resource consumption. Its features include: small size, fast startup, low memory usage, improved response speed and throughput, and reduced resource consumption. Practical case: SlimFramework creates REST API, only 500KB, high responsiveness and high throughput

Golang framework documentation best practices Golang framework documentation best practices Jun 04, 2024 pm 05:00 PM

Writing clear and comprehensive documentation is crucial for the Golang framework. Best practices include following an established documentation style, such as Google's Go Coding Style Guide. Use a clear organizational structure, including headings, subheadings, and lists, and provide navigation. Provides comprehensive and accurate information, including getting started guides, API references, and concepts. Use code examples to illustrate concepts and usage. Keep documentation updated, track changes and document new features. Provide support and community resources such as GitHub issues and forums. Create practical examples, such as API documentation.

How does the learning curve of PHP frameworks compare to other language frameworks? How does the learning curve of PHP frameworks compare to other language frameworks? Jun 06, 2024 pm 12:41 PM

The learning curve of a PHP framework depends on language proficiency, framework complexity, documentation quality, and community support. The learning curve of PHP frameworks is higher when compared to Python frameworks and lower when compared to Ruby frameworks. Compared to Java frameworks, PHP frameworks have a moderate learning curve but a shorter time to get started.

How to choose the best golang framework for different application scenarios How to choose the best golang framework for different application scenarios Jun 05, 2024 pm 04:05 PM

Choose the best Go framework based on application scenarios: consider application type, language features, performance requirements, and ecosystem. Common Go frameworks: Gin (Web application), Echo (Web service), Fiber (high throughput), gorm (ORM), fasthttp (speed). Practical case: building REST API (Fiber) and interacting with the database (gorm). Choose a framework: choose fasthttp for key performance, Gin/Echo for flexible web applications, and gorm for database interaction.

Performance comparison of Java frameworks Performance comparison of Java frameworks Jun 04, 2024 pm 03:56 PM

According to benchmarks, for small, high-performance applications, Quarkus (fast startup, low memory) or Micronaut (TechEmpower excellent) are ideal choices. SpringBoot is suitable for large, full-stack applications, but has slightly slower startup times and memory usage.

Detailed practical explanation of golang framework development: Questions and Answers Detailed practical explanation of golang framework development: Questions and Answers Jun 06, 2024 am 10:57 AM

In Go framework development, common challenges and their solutions are: Error handling: Use the errors package for management, and use middleware to centrally handle errors. Authentication and authorization: Integrate third-party libraries and create custom middleware to check credentials. Concurrency processing: Use goroutines, mutexes, and channels to control resource access. Unit testing: Use gotest packages, mocks, and stubs for isolation, and code coverage tools to ensure sufficiency. Deployment and monitoring: Use Docker containers to package deployments, set up data backups, and track performance and errors with logging and monitoring tools.

See all articles