MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction

• URL: http://arxiv.org/abs/2409.18737v2
• Date: Fri, 22 Nov 2024 05:37:23 GMT
• Title: MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction
• Authors: Jingyu Song, Xudong Chen, Liupei Lu, Jie Li, Katherine A. Skinner,
• Abstract summary: We propose a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction. Specifically, we contribute a working memory fusion module that improves the model's memory capacity to reason across a history of frames. We also design a novel temporal overlap heatmap to explicitly inform the model about the temporal overlap information and vehicle trajectory.
• Score: 6.743612231580936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-definition (HD) maps provide environmental information for autonomous driving systems and are essential for safe planning. While existing methods with single-frame input achieve impressive performance for online vectorized HD map construction, they still struggle with complex scenarios and occlusions. We propose MemFusionMap, a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction. Specifically, we contribute a working memory fusion module that improves the model's memory capacity to reason across a history of frames. We also design a novel temporal overlap heatmap to explicitly inform the model about the temporal overlap information and vehicle trajectory in the Bird's Eye View space. By integrating these two designs, MemFusionMap significantly outperforms existing methods while also maintaining a versatile design for scalability. We conduct extensive evaluation on open-source benchmarks and demonstrate a maximum improvement of 5.4% in mAP over state-of-the-art methods. The project page for MemFusionMap is https://song-jingyu.github.io/MemFusionMap

Related papers

• DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusion [14.872416661028144]
  We propose DiffSemanticFusion -- a fusion framework for trajectory prediction and planning.<n>Our approach reasons over a semantic-fused BEV space, enhanced by a map diffusion module.<n>Experiments on real-world autonomous driving benchmarks, nuScenes and NAVSIM, demonstrate improved performance over several state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-03T14:32:05Z)
• MambaMap: Online Vectorized HD Map Construction using State Space Model [11.15033113060733]
  MambaMap is a novel framework that efficiently fuses long-range temporal features in the state space to construct online vectorized HD maps.<n>Specifically, MambaMap incorporates a memory bank to store and utilize information from historical frames.<n>In addition, we design innovative multi-directional and spatial-temporal scanning strategies to enhance feature extraction at both BEV and instance levels.
  arXiv  Detail & Related papers  (2025-07-27T11:09:27Z)
• Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Construction [9.166949877822807]
  We present Uni-PrevPredMap, a unified prior-informed framework that integrates previous predictions and simulated outdated HD maps. Uni-PrevPredMap achieves state-of-the-art performance in map-absent scenarios across established online vectorized HD map construction benchmarks.
  arXiv  Detail & Related papers  (2025-04-09T07:36:17Z)
• MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction [23.212961039696722]
  We propose MapFusion, a novel multi-modal Bird's-Eye View (BEV) feature fusion method for map construction. We introduce the Cross-modal Interaction Transform (CIT) module, enabling interaction between two BEV feature spaces. We also propose an effective Dual Dynamic Fusion (DDF) module to adaptively select valuable information from different modalities.
  arXiv  Detail & Related papers  (2025-02-05T16:25:45Z)
• TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior [70.84644266024571]
  We propose to train a perception model to "see" standard definition maps (SDMaps) We encode SDMap elements into neural spatial map representations and instance tokens, and then incorporate such complementary features as prior information. Based on the lane segment representation framework, the model simultaneously predicts lanes, centrelines and their topology.
  arXiv  Detail & Related papers  (2024-11-22T06:13:42Z)
• Neural Semantic Map-Learning for Autonomous Vehicles [85.8425492858912]
  We present a mapping system that fuses local submaps gathered from a fleet of vehicles at a central instance to produce a coherent map of the road environment. Our method jointly aligns and merges the noisy and incomplete local submaps using a scene-specific Neural Signed Distance Field. We leverage memory-efficient sparse feature-grids to scale to large areas and introduce a confidence score to model uncertainty in scene reconstruction.
  arXiv  Detail & Related papers  (2024-10-10T10:10:03Z)
• GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction [20.1127163541618]
  We have designed a universal map generation framework, GenMapping. The framework is established with a triadic synergy architecture, including principal and dual auxiliary branches. A thorough array of experimental results shows that the proposed model surpasses current state-of-the-art methods in both semantic mapping and vectorized mapping, while also maintaining a rapid inference speed.
  arXiv  Detail & Related papers  (2024-09-13T10:15:28Z)
• Enhancing Vectorized Map Perception with Historical Rasterized Maps [37.48510990922406]
  We propose HRMapNet, leveraging a low-cost Historical Rasterized Map to enhance online vectorized map perception. The historicalized map can be easily constructed from past predicted vectorized results and provides valuable complementary information. HRMapNet can be integrated with most online vectorized map perception methods.
  arXiv  Detail & Related papers  (2024-09-01T05:22:33Z)
• LGmap: Local-to-Global Mapping Network for Online Long-Range Vectorized HD Map Construction [0.3883607294385062]
  This report introduces the first-place winning solution for the Autonomous Grand Challenge 2024 - Mapless Driving. We introduce a novel online mapping pipeline LGmap, which adept at long-range temporal model. Our method achieves 0.66 UniScore in the Mapless Driving OpenLaneV2 test set.
  arXiv  Detail & Related papers  (2024-06-20T04:29:58Z)
• MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction [40.07726377230152]
  High-definition (HD) map provides abundant and precise static environmental information of the driving scene. We present textbfMap textbfTRansformer, an end-to-end framework for online vectorized HD map construction.
  arXiv  Detail & Related papers  (2023-08-10T17:56:53Z)
• ConceptFusion: Open-set Multimodal 3D Mapping [91.23054486724402]
  ConceptFusion is a scene representation that is fundamentally open-set. It enables reasoning beyond a closed set of concepts and inherently multimodal. We evaluate ConceptFusion on a number of real-world datasets.
  arXiv  Detail & Related papers  (2023-02-14T18:40:26Z)
• HDMapNet: An Online HD Map Construction and Evaluation Framework [23.19001503634617]
  HD map construction is a crucial problem for autonomous driving. Traditional HD maps are coupled with centimeter-level accurate localization which is unreliable in many scenarios. Online map learning is a more scalable way to provide semantic and geometry priors to self-driving vehicles.
  arXiv  Detail & Related papers  (2021-07-13T18:06:46Z)
• HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps [81.86923212296863]
  HD maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. There are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack. We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps.
  arXiv  Detail & Related papers  (2021-06-28T17:59:30Z)
• Label Decoupling Framework for Salient Object Detection [157.96262922808245]
  Recent methods mainly focus on aggregating multi-level features from convolutional network (FCN) and introducing edge information as auxiliary supervision. We propose a label decoupling framework (LDF) which consists of a label decoupling procedure and a feature interaction network (FIN) Experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.
  arXiv  Detail & Related papers  (2020-08-25T14:23:38Z)
• RoutedFusion: Learning Real-time Depth Map Fusion [73.0378509030908]
  We present a novel real-time capable machine learning-based method for depth map fusion. We propose a neural network that predicts non-linear updates to better account for typical fusion errors. Our network is composed of a 2D depth routing network and a 3D depth fusion network which efficiently handle sensor-specific noise and outliers.
  arXiv  Detail & Related papers  (2020-01-13T16:46:41Z)

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.