Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving

• URL: http://arxiv.org/abs/2504.01023v1
• Date: Wed, 26 Mar 2025 00:07:21 GMT
• Title: Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving
• Authors: Chaofan Wu, Jiaheng Li, Jinghao Cao, Ming Li, Yongkang Feng, Jiayu Wu Shuwen Xu, Zihang Gao, Sidan Du, Yang Li,
• Abstract summary: We use omnidirectional depth estimation to introduce prior.<n>We also introduce a cylindrical voxel representation based on polar coordinate to better align with panoramic camera views.<n> Experimental results demonstrate that our Sketch- network significantly enhances 3D perception performance.
• Score: 7.3709535266926025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.

Related papers

• MagicDrive: Street View Generation with Diverse 3D Geometry Control [82.69871576797166]
  We introduce MagicDrive, a novel street view generation framework, offering diverse 3D geometry controls. Our design incorporates a cross-view attention module, ensuring consistency across multiple camera views.
  arXiv  Detail & Related papers  (2023-10-04T06:14:06Z)
• 3D Data Augmentation for Driving Scenes on Camera [50.41413053812315]
  We propose a 3D data augmentation approach termed Drive-3DAug, aiming at augmenting the driving scenes on camera in the 3D space. We first utilize Neural Radiance Field (NeRF) to reconstruct the 3D models of background and foreground objects. Then, augmented driving scenes can be obtained by placing the 3D objects with adapted location and orientation at the pre-defined valid region of backgrounds.
  arXiv  Detail & Related papers  (2023-03-18T05:51:05Z)
• Scene-aware Egocentric 3D Human Pose Estimation [72.57527706631964]
  Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. We propose a scene-aware egocentric pose estimation method that guides the prediction of the egocentric pose with scene constraints.
  arXiv  Detail & Related papers  (2022-12-20T21:35:39Z)
• PolarFormer: Multi-camera 3D Object Detection with Polar Transformers [93.49713023975727]
  3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world. Existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. We propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images.
  arXiv  Detail & Related papers  (2022-06-30T16:32:48Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)
• Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data [80.14669385741202]
  We propose a self-supervised pre-training method for 3D perception models tailored to autonomous driving data. We leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups. Our method does not require any point cloud nor image annotations.
  arXiv  Detail & Related papers  (2022-03-30T12:40:30Z)
• Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task [48.555440807415664]
  We present the first high-diversity challenging Roadside Perception 3D dataset- Rope3D from a novel view. The dataset consists of 50k images and over 1.5M 3D objects in various scenes. We propose to leverage the geometry constraint to solve the inherent ambiguities caused by various sensors, viewpoints.
  arXiv  Detail & Related papers  (2022-03-25T12:13:23Z)
• Monocular Road Planar Parallax Estimation [25.36368935789501]
  Estimating the 3D structure of the drivable surface and surrounding environment is a crucial task for assisted and autonomous driving. We propose Road Planar Parallax Attention Network (RPANet), a new deep neural network for 3D sensing from monocular image sequences. RPANet takes a pair of images aligned by the homography of the road plane as input and outputs a $gamma$ map for 3D reconstruction.
  arXiv  Detail & Related papers  (2021-11-22T10:03:41Z)
• Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras [3.485767750936058]
  Multidimensional Vector is proposed to include the utilizable information generated in different dimensions and stages. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.
  arXiv  Detail & Related papers  (2021-07-19T13:24:21Z)
• Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning Approach [10.610403488989428]
  We propose a framework that estimates the 3D positions of semantically meaningful landmarks without assuming known camera intrinsics. We utilize multi-view geometry as well as deep learning based self-calibration, depth, and ego-motion estimation for traffic sign positioning. We achieve an average single-journey relative and absolute positioning accuracy of 39cm and 1.26m respectively.
  arXiv  Detail & Related papers  (2020-07-25T12:10:16Z)
• 3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning [11.599633757222406]
  Recently end-to-end approaches based on convolutional neural network have been much studied to achieve or even exceed 3D-geometry based traditional methods. In this work, we propose a compact network for absolute camera pose regression. Inspired from those traditional methods, a 3D scene geometry-aware constraint is also introduced by exploiting all available information including motion, depth and image contents.
  arXiv  Detail & Related papers  (2020-05-13T04:15:14Z)

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.