STELLAR: Scaling 3D Perception Large Models for Autonomous Driving

• URL: http://arxiv.org/abs/2605.20390v1
• Date: Tue, 19 May 2026 18:40:20 GMT
• Title: STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
• Abstract summary: We develop our STELLAR model based on Sparse Window Transformer, by extending the input modalities to include LiDAR, radar, camera, and map prior.<n>We train the model on a large-scale dataset of 50 million driving examples with up to 500 million parameters.<n>Our work demonstrates that large-scale training is a highly promising path for advancing the capabilities of perception models for autonomous driving.
• Score: 38.138694493703504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model scaling has demonstrated remarkable success through large-scale training on diverse datasets. It remains an open question whether the same paradigm would apply to autonomous driving perception systems due to unique challenges, such as fusing heterogeneous sensor data and the need for sophisticated 3D spatial understanding. To bridge this gap, we present a comprehensive study on systematically analyzing the impact of scale on these systems. We develop our STELLAR model based on Sparse Window Transformer, by extending the input modalities to include LiDAR, radar, camera, and map prior. We train the model on a large-scale dataset of 50 million driving examples with up to 500 million parameters. Our large-scale experiments reveal empirical scaling trends that connect model performance to model size, data, and compute. The resulting model establishes a new state-of-the-art on the Waymo Open Dataset challenge, outperforming prior arts by a large margin. Our work demonstrates that large-scale training is a highly promising path for advancing the capabilities of perception models for autonomous driving.

Related papers

• Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving [46.24100810736637]
  We introduce a self-supervised pre-training framework that learns effective 3D representations from scratch on unlabeled data.<n>The approach significantly improves model performance on downstream tasks such as 3D object detection, BEV segmentation, 3D object tracking, and occupancy prediction.
  arXiv  Detail & Related papers  (2025-04-17T07:26:11Z)
• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [88.85002707211777]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets.<n>Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds.<n>This alignment facilitates cross-modal representation learning, enhancing the semantic consistency between 2D and 3D data.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• Pretraining Billion-scale Geospatial Foundational Models on Frontier [0.16492989697868893]
  Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy.
  arXiv  Detail & Related papers  (2024-04-17T19:16:32Z)
• Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities [59.02391344178202]
  Vision foundation models (VFMs) serve as potent building blocks for a wide range of AI applications. The scarcity of comprehensive training data, the need for multi-sensor integration, and the diverse task-specific architectures pose significant obstacles to the development of VFMs. This paper delves into the critical challenge of forging VFMs tailored specifically for autonomous driving, while also outlining future directions.
  arXiv  Detail & Related papers  (2024-01-16T01:57:24Z)
• HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving [95.42203932627102]
  3D human pose estimation is an emerging technology, which can enable the autonomous vehicle to perceive and understand the subtle and complex behaviors of pedestrians. Our method efficiently makes use of these complementary signals, in a semi-supervised fashion and outperforms existing methods with a large margin. Specifically, we embed LiDAR points into pixel-aligned multi-modal features, which we pass through a sequence of Transformer refinement stages.
  arXiv  Detail & Related papers  (2022-12-15T11:15:14Z)
• SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving [94.11868795445798]
  We release a Large-Scale Object Detection benchmark for Autonomous driving, named as SODA10M, containing 10 million unlabeled images and 20K images labeled with 6 representative object categories. To improve diversity, the images are collected every ten seconds per frame within 32 different cities under different weather conditions, periods and location scenes. We provide extensive experiments and deep analyses of existing supervised state-of-the-art detection models, popular self-supervised and semi-supervised approaches, and some insights about how to develop future models.
  arXiv  Detail & Related papers  (2021-06-21T13:55:57Z)
• One Million Scenes for Autonomous Driving: ONCE Dataset [91.94189514073354]
  We introduce the ONCE dataset for 3D object detection in the autonomous driving scenario. The data is selected from 144 driving hours, which is 20x longer than the largest 3D autonomous driving dataset available. We reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
  arXiv  Detail & Related papers  (2021-06-21T12:28:08Z)
• An LSTM-Based Autonomous Driving Model Using Waymo Open Dataset [7.151393153761375]
  This paper introduces an approach to learn a short-term memory (LSTM)-based model for imitating the behavior of a self-driving model. The experimental results show that our model outperforms several models in driving action prediction.
  arXiv  Detail & Related papers  (2020-02-14T05:28:15Z)

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.