paper-with-me

홈 › Papers

LMFormer: Lane based Motion Prediction Transformer

2025-04-14 · Harsh Yadav, Maximilian Schaefer, Kun Zhao, Tobias Meisen

Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance.

📄 PDF Abstract BibTeX arXiv:2504.10275

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingBenchmarkingmotion predictionPredictionTrajectory Prediction

Similar Papers 제목 키워드 기반

ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer

2022-08-31 · Jiaqi Ma, Shengyuan Yan, Lefei Zhang, Guoli Wang 외

In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contain…

AttributeDeblurringDenoisingImage Restoration

NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity

2025-06-06 · Adrien Petralia, Philippe Charpentier, Youssef Kadhi, Themis Palpanas

Millions of smart meters have been deployed worldwide, collecting the total power consumed by individual households. Based on these data, electricity suppliers offer their clients energy monitoring solutions to provide f…

Non-Intrusive Load Monitoring

Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System

2022-07-16 · Mingjie Li, Rui Liu, Guangsi Shi, Mingfei Han 외

Long-term time-series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. Howev…

Data AugmentationDecoderTime SeriesTime Series Analysis+1

Temporal Triplane Transformers as Occupancy World Models

2025-03-10 · Haoran Xu, Peixi Peng, Guang Tan, Yiqian Chang 외

World models aim to learn or construct representations of the environment that enable the prediction of future scenes, thereby supporting intelligent motion planning. However, existing models often struggle to produce fi…

Autonomous DrivingMotion Planning

Motion-Plane-Adaptive Inter Prediction in 360-Degree Video Coding

2022-02-07 · Andy Regensky, Christian Herglotz, André Kaup

Inter prediction is one of the key technologies enabling the high compression efficiency of modern video coding standards. 360-degree video needs to be mapped to the 2D image plane prior to coding in order to allow compr…

Prediction