RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception

• URL: http://arxiv.org/abs/2405.09883v4
• Date: Thu, 4 Jul 2024 15:14:18 GMT
• Title: RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception
• Authors: Xiaosu Zhu, Hualian Sheng, Sijia Cai, Bing Deng, Shaopeng Yang, Qiao Liang, Ken Chen, Lianli Gao, Jingkuan Song, Jieping Ye,
• Abstract summary: RoScenes is the largest multi-view roadside perception dataset. Our dataset achieves surprising 21.13M 3D annotations within 64,000 $m2$.
• Score: 98.76525636842177
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes. The highlights of RoScenes include significantly large perception area, full scene coverage and crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D annotations within 64,000 $m^2$. To relieve the expensive costs of roadside 3D labeling, we present a novel BEV-to-3D joint annotation pipeline to efficiently collect such a large volume of data. After that, we organize a comprehensive study for current BEV methods on RoScenes in terms of effectiveness and efficiency. Tested methods suffer from the vast perception area and variation of sensor layout across scenes, resulting in performance levels falling below expectations. To this end, we propose RoBEV that incorporates feature-guided position embedding for effective 2D-3D feature assignment. With its help, our method outperforms state-of-the-art by a large margin without extra computational overhead on validation set. Our dataset and devkit will be made available at https://github.com/xiaosu-zhu/RoScenes.

Related papers

• ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object [14.219472370221029]
  We propose 2D Region-oriented Attention for a BEV-based 3D Object Detection Network (ROA-BEV) Our method increases the information content of ROA through a multi-scale structure. Experiments on nuScenes show that ROA-BEV improves the performance based on BEVDet and BEVDepth.
  arXiv  Detail & Related papers  (2024-10-14T08:51:56Z)
• Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance [11.090775523892074]
  We introduce a novel semi-supervised framework to alleviate the dependency on densely annotated data. Our approach leverages 2D foundation models to generate essential 3D scene geometric and semantic cues. Our method achieves up to 85% of the fully-supervised performance using only 10% labeled data.
  arXiv  Detail & Related papers  (2024-08-21T12:13:18Z)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• SGV3D:Towards Scenario Generalization for Vision-based Roadside 3D Object Detection [27.991404725024953]
  Current vision-based roadside detection methods possess high accuracy on labeled scenes but have inferior performance on new scenes. This is because roadside cameras remain stationary after installation, resulting in the algorithm overfitting these roadside backgrounds and camera poses. We propose an innovative Scenario Generalization Framework for Vision-based Roadside 3D Object Detection, dubbed SGV3D.
  arXiv  Detail & Related papers  (2024-01-29T12:31:13Z)
• SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving [98.74706005223685]
  3D scene understanding plays a vital role in vision-based autonomous driving. We propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
  arXiv  Detail & Related papers  (2023-03-16T17:59:08Z)
• ONCE-3DLanes: Building Monocular 3D Lane Detection [41.46466150783367]
  We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. By exploiting the explicit relationship between point clouds and image pixels, a dataset annotation pipeline is designed to automatically generate high-quality 3D lane locations.
  arXiv  Detail & Related papers  (2022-04-30T16:35:25Z)
• From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection [101.20784125067559]
  We propose a new architecture, namely Hallucinated Hollow-3D R-CNN, to address the problem of 3D object detection. In our approach, we first extract the multi-view features by sequentially projecting the point clouds into the perspective view and the bird-eye view. The 3D objects are detected via a box refinement module with a novel Hierarchical Voxel RoI Pooling operation.
  arXiv  Detail & Related papers  (2021-07-30T02:00:06Z)
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [93.51773847125014]
  We propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world.
  arXiv  Detail & Related papers  (2020-12-22T22:43:35Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)

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.