Real-time Multi-view Omnidirectional Depth Estimation for Real Scenarios based on Teacher-Student Learning with Unlabeled Data

• URL: http://arxiv.org/abs/2409.07843v2
• Date: Sun, 09 Nov 2025 17:06:55 GMT
• Title: Real-time Multi-view Omnidirectional Depth Estimation for Real Scenarios based on Teacher-Student Learning with Unlabeled Data
• Authors: Ming Li, Xiong Yang, Chaofan Wu, Jiaheng Li, Pinzhi Wang, Xuejiao Hu, Sidan Du, Yang Li,
• Abstract summary: We propose a real-time omnidirectional depth estimation method for edge computing platforms named Rt- OmniMVS.<n>To achieve high accuracy, robustness, and generalization in real-world environments, we introduce a teacher-student learning strategy.<n>We also propose HexaMODE, an omnidirectional depth sensing system based on multi-view fisheye cameras and edge device.
• Score: 13.107135855680992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Omnidirectional depth estimation enables efficient 3D perception over a full 360-degree range. However, in real-world applications such as autonomous driving and robotics, achieving real-time performance and robust cross-scene generalization remains a significant challenge for existing algorithms. In this paper, we propose a real-time omnidirectional depth estimation method for edge computing platforms named Rt-OmniMVS, which introduces the Combined Spherical Sweeping method and implements the lightweight network structure to achieve real-time performance on edge computing platforms. To achieve high accuracy, robustness, and generalization in real-world environments, we introduce a teacher-student learning strategy. We leverage the high-precision stereo matching method as the teacher model to predict pseudo labels for unlabeled real-world data, and utilize data and model augmentation techniques for training to enhance performance of the student model Rt-OmniMVS. We also propose HexaMODE, an omnidirectional depth sensing system based on multi-view fisheye cameras and edge computation device. A large-scale hybrid dataset contains both unlabeled real-world data and synthetic data is collected for model training. Experiments on public datasets demonstrate that proposed method achieves results comparable to state-of-the-art approaches while consuming significantly less resource. The proposed system and algorithm also demonstrate high accuracy in various complex real-world scenarios, both indoors and outdoors, achieving an inference speed of 15 frames per second on edge computing platforms.

Related papers

• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving [62.9051914830949]
  We present ROVR, a large-scale, diverse, and cost-efficient depth dataset designed to capture the complexity of real-world driving.<n>A lightweight acquisition pipeline ensures scalable collection, while sparse but statistically sufficient ground truth supports robust training.<n> Benchmarking with state-of-the-art monocular depth models reveals severe cross-dataset generalization failures.
  arXiv  Detail & Related papers  (2025-08-19T16:13:49Z)
• Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data [0.0]
  This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection.<n>Unlike conventional distillation methods that require separate teacher and student models, the proposed framework utilizes a smoothed, historical version of the model itself as the teacher.<n> Experimental results show that Smooth-Distill consistently outperforms alternative approaches across different evaluation scenarios.
  arXiv  Detail & Related papers  (2025-06-27T06:51:51Z)
• Private Training & Data Generation by Clustering Embeddings [74.00687214400021]
  Differential privacy (DP) provides a robust framework for protecting individual data.<n>We introduce a novel principled method for DP synthetic image embedding generation.<n> Empirically, a simple two-layer neural network trained on synthetically generated embeddings achieves state-of-the-art (SOTA) classification accuracy.
  arXiv  Detail & Related papers  (2025-06-20T00:17:14Z)
• TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation [19.488886693695946]
  TartanGround is a large-scale, multi-modal dataset to advance the perception and autonomy of ground robots.<n>We collect 910 trajectories across 70 environments, resulting in 1.5 million samples.<n>TartanGround can serve as a testbed for training and evaluation of a broad range of learning-based tasks.
  arXiv  Detail & Related papers  (2025-05-15T20:35:06Z)
• Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model [62.37493746544967]
  Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps. Existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments. We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation.
  arXiv  Detail & Related papers  (2025-03-30T16:24:22Z)
• Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process [14.428139979659395]
  Terrain analysis is critical for the practical application of ground mobile robots in real-world tasks. We propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to navigate through complex terrains. We develop an autonomous navigation framework integrated with the traversability map and validate it with a differential driven vehicle in complex outdoor environments.
  arXiv  Detail & Related papers  (2025-03-06T06:26:57Z)
• A Practical Approach to Underwater Depth and Surface Normals Estimation [3.0516727053033392]
  This paper presents a novel deep learning model for Monocular Depth and Surface Normals Estimation (MDSNE)<n>It is specifically tailored for underwater environments, using a hybrid architecture that integrates CNNs with Transformers.<n>Our model reduces parameters by 90% and training costs by 80%, allowing real-time 3D perception on resource-constrained devices.
  arXiv  Detail & Related papers  (2024-10-02T22:41:12Z)
• OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
  We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
  arXiv  Detail & Related papers  (2024-09-14T07:44:22Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Enhancing Navigation Benchmarking and Perception Data Generation for Row-based Crops in Simulation [0.3518016233072556]
  This paper presents a synthetic dataset to train semantic segmentation networks and a collection of virtual scenarios for a fast evaluation of navigation algorithms. An automatic parametric approach is developed to explore different field geometries and features. The simulation framework and the dataset have been evaluated by training a deep segmentation network on different crops and benchmarking the resulting navigation.
  arXiv  Detail & Related papers  (2023-06-27T14:46:09Z)
• Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing [77.34726150561087]
  This paper describes how advanced deep learning based computer vision algorithms are applied to enable real-time on-board sensor processing for small UAVs. All algorithms have been developed using state-of-the-art image processing methods based on deep neural networks.
  arXiv  Detail & Related papers  (2022-11-02T11:10:42Z)
• Deterministic and Stochastic Analysis of Deep Reinforcement Learning for Low Dimensional Sensing-based Navigation of Mobile Robots [0.41562334038629606]
  This paper presents a comparative analysis of two Deep-RL techniques - Deep Deterministic Policy Gradients (DDPG) and Soft Actor-Critic (SAC) We aim to contribute by showing how the neural network architecture influences the learning itself, presenting quantitative results based on the time and distance of aerial mobile robots for each approach.
  arXiv  Detail & Related papers  (2022-09-13T22:28:26Z)
• Semi-Perspective Decoupled Heatmaps for 3D Robot Pose Estimation from Depth Maps [66.24554680709417]
  Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications. We propose a non-invasive framework based on depth devices and deep neural networks to estimate the 3D pose of robots from an external camera.
  arXiv  Detail & Related papers  (2022-07-06T08:52:12Z)
• Neural Scene Representation for Locomotion on Structured Terrain [56.48607865960868]
  We propose a learning-based method to reconstruct the local terrain for a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the estimates the topography in the robot's vicinity. We propose a 3D reconstruction model that faithfully reconstructs the scene, despite the noisy measurements and large amounts of missing data coming from the blind spots of the camera arrangement.
  arXiv  Detail & Related papers  (2022-06-16T10:45:17Z)
• Pushing the Limits of Learning-based Traversability Analysis for Autonomous Driving on CPU [1.841057463340778]
  This paper proposes and evaluates a real-time machine learning-based Traversability Analysis method. We show that integrating a new set of geometric and visual features and focusing on important implementation details enables a noticeable boost in performance and reliability. The proposed approach has been compared with state-of-the-art Deep Learning approaches on a public dataset of outdoor driving scenarios.
  arXiv  Detail & Related papers  (2022-06-07T07:57:34Z)
• 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)
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World [83.36195426897768]
  We propose VRVO, a novel framework for retrieving the absolute scale from virtual data. We first train a scale-aware disparity network using both monocular real images and stereo virtual data. The resulting scale-consistent disparities are then integrated with a direct VO system.
  arXiv  Detail & Related papers  (2022-03-11T01:51:54Z)
• High-Speed Robot Navigation using Predicted Occupancy Maps [0.0]
  We study algorithmic approaches that allow the robot to predict spaces extending beyond the sensor horizon for robust planning at high speeds. We accomplish this using a generative neural network trained from real-world data without requiring human annotated labels. We extend our existing control algorithms to support leveraging the predicted spaces to improve collision-free planning and navigation at high speeds.
  arXiv  Detail & Related papers  (2020-12-22T16:25:12Z)
• Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance [95.86944752753564]
  We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties. Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates. The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
  arXiv  Detail & Related papers  (2020-07-28T07:34:30Z)
• OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems [88.41004332322788]
  We present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation. We integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency.
  arXiv  Detail & Related papers  (2020-03-18T05:52:10Z)

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.