Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset
Yiming Li, Zhiheng Li, Nuo Chen, Moonjun Gong, Zonglin Lyu, Zehong Wang, Peili Jiang, Chen Feng
摘要
Surround-view RGB images (a) (b) (c) (d) Figure 1. Overview of MARS. (a) Within a geographical area, we operate four autonomous vehicles, displaying their GPS trajectories from a single day using different colors. (b) Vehicles occasionally come close together (visualized via distinct-colored point clouds), supporting research in multiagent systems. (c) We collect sensory data from repeated traversals of the same location under varying conditions, for learning and perception research with retrospective memory. (d) The dataset includes surround-view RGB images and LiDAR point clouds for cross-modal perception and learning. Note that our data is obtained from May Mobility : https://maymobility.com/ .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- Adversarial Exploitation of Data Diversity Improves Visual LocalizationSihang Li, Siqi Tan, Bowen Chang, Jing Zhang 等ICCV 2025 · 被引用 4 次
- Extrapolated Urban View Synthesis BenchmarkXiangyu Han, Zhen Jia, Boyi Li, Yan Wang 等ICCV 2025 · 被引用 3 次
- LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature GenerationZijie Wang, Weiming Zhang, Wei Zhang, Xiao Tan 等ICCV 2025 · 被引用 2 次
- GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature SpaceWentao Wang, Haoran Xu, Guang TanICLR 2026 · 被引用 2 次
- Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X CollaborationKatie Z. Luo, Minh-Quan Dao, Zhenzhen Liu, Mark E. Campbell 等ICCV 2025 · 被引用 2 次
它引用的顶会 Paper27
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- SegFormer: Simple and Efficient Design for Semantic Segmentation with TransformersEnze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar 等NeurIPS 2021 · 被引用 9,661 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion DatasetScott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu 等ICCV 2021 · 被引用 817 次
相关 Paper
- V2U4Real: A Real-world Large-scale Dataset for Vehicle-to-UAV Cooperative PerceptionWeijia Li, Haoen Xiang, Tianxu Wang, Shuaibing Wu 等CVPR 2026 · 被引用 4 次
- V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative PerceptionRunsheng Xu, Xin Xia, Jinlong Li, Hanzhao Li 等CVPR 2023
- MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point CloudsJiahui Liu, Chirui Chang, Jianhui Liu, Xiaoyang Wu 等CVPR 2023
- Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather ConditionsCarlos Andres Diaz-Ruiz, Youya Xia, Yurong You, Jose Nino 等CVPR 2022 · 被引用 51 次
- Unsupervised Multi-agent and Single-agent Perception from Cooperative ViewsHaochen Yang, Baolu Li, Lei Li, Delin Ren 等CVPR 2026 · 被引用 2 次
