# THMA: Tencent HD Map AI System for Creating HD Map Annotations

arXiv: https://arxiv.org/abs/2212.11123 · HTML: https://mlsanity.com/paper/2212.11123/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [Hierarchical Multi-Scale Attention for Semantic Segmentation](https://mlsanity.com/paper/2005.10821/) (2020)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [Baidu Apollo EM Motion Planner](https://mlsanity.com/paper/1807.08048/) (2018)
- [HDNET: Exploiting HD Maps for 3D Object Detection](https://mlsanity.com/paper/2012.11704/) (2020)
- [Scalable Active Learning for Object Detection](https://mlsanity.com/paper/2004.04699/) (2020)
- [Automatic Construction of Lane-level HD Maps for Urban Scenes](https://mlsanity.com/paper/2107.10972/) (2021)
- [Automatic Building and Labeling of HD Maps with Deep Learning](https://mlsanity.com/paper/2006.00644/) (2020)

## Built on by (most cited first, 9 of 9)

- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles](https://mlsanity.com/paper/2310.08034/) (2023)
- [Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models](https://mlsanity.com/paper/2502.06419/) (2025)
- [MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation](https://mlsanity.com/paper/2407.11682/) (2024)
- [GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction](https://mlsanity.com/paper/2409.10063/) (2024)
- [CEMFormer: Learning to Predict Driver Intentions from In-Cabin and External Cameras via Spatial-Temporal Transformers](https://mlsanity.com/paper/2305.07840/) (2023)
- [RTMap: Real-Time Recursive Mapping with Change Detection and Localization](https://mlsanity.com/paper/2507.00980/) (2025)
- [A Survey on Large Language Model-empowered Autonomous Driving](https://mlsanity.com/paper/2409.14165/) (2024)
- [Localization-Guided Foreground Augmentation in Autonomous Driving](https://mlsanity.com/paper/2604.18940/) (2026)

## Abstract (arXiv)

Nowadays, autonomous vehicle technology is becoming more and more mature. Critical to progress and safety, high-definition (HD) maps, a type of centimeter-level map collected using a laser sensor, provide accurate descriptions of the surrounding environment. The key challenge of HD map production is efficient, high-quality collection and annotation of large-volume datasets. Due to the demand for high quality, HD map production requires significant manual human effort to create annotations, a very time-consuming and costly process for the map industry. In order to reduce manual annotation burdens, many artificial intelligence (AI) algorithms have been developed to pre-label the HD maps. However, there still exists a large gap between AI algorithms and the traditional manual HD map production pipelines in accuracy and robustness. Furthermore, it is also very resource-costly to build large-scale annotated datasets and advanced machine learning algorithms for AI-based HD map automatic labeling systems. In this paper, we introduce the Tencent HD Map AI (THMA) system, an innovative end-to-end, AI-based, active learning HD map labeling system capable of producing and labeling HD maps with a scale of hundreds of thousands of kilometers. In THMA, we train AI models directly from massive HD map datasets via supervised, self-supervised, and weakly supervised learning to achieve high accuracy and efficiency required by downstream users. THMA has been deployed by the Tencent Map team to provide services to downstream companies and users, serving over 1,000 labeling workers and producing more than 30,000 kilometers of HD map data per day at most. More than 90 percent of the HD map data in Tencent Map is labeled automatically by THMA, accelerating the traditional HD map labeling process by more than ten times.