URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation

• URL: http://arxiv.org/abs/2509.18184v1
• Date: Thu, 18 Sep 2025 07:24:50 GMT
• Title: URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation
• Abstract summary: Event cameras offer high temporal resolution, high dynamic range, and low latency.<n>We introduce an uncertainty-aware refinement network called URNet for event-based stereo depth estimation.
• Score: 35.032297238013186
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Event cameras provide high temporal resolution, high dynamic range, and low latency, offering significant advantages over conventional frame-based cameras. In this work, we introduce an uncertainty-aware refinement network called URNet for event-based stereo depth estimation. Our approach features a local-global refinement module that effectively captures fine-grained local details and long-range global context. Additionally, we introduce a Kullback-Leibler (KL) divergence-based uncertainty modeling method to enhance prediction reliability. Extensive experiments on the DSEC dataset demonstrate that URNet consistently outperforms state-of-the-art (SOTA) methods in both qualitative and quantitative evaluations.

Related papers

• VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding [14.359441996020719]
  We present VEOcc, a voxel-centric framework formulated as a perception-and-assimilation paradigm.<n>By eliminating the need for initial scale estimation, VEOcc enables highly streamlined, open-ended map expansion.<n>Experiments on Occ-ScanNet and EmbodiedOcc-ScanNet demonstrate that VEOcc establishes new state-of-the-art performance in both local and embodied settings.
  arXiv  Detail & Related papers  (2026-05-24T13:10:43Z)
• Compressive sensing inspired self-supervised single-pixel imaging [48.79613794195208]
  SISTA-Net is a compressive sensing-inspired self-supervised method for single-pixel imaging.<n>We leverage deep nonlinear networks as adaptive sparse transforms combined with a learnable soft-thresholding operator to impose explicit physical sparsity in the latent domain.<n>Experiments on multiple simulation scenarios demonstrate that SISTA-Net outperforms state-of-the-art methods by 2.6 dB in PSNR.
  arXiv  Detail & Related papers  (2026-03-31T13:31:43Z)
• Rethinking SAR ATR: A Target-Aware Frequency-Spatial Enhancement Framework with Noise-Resilient Knowledge Guidance [2.0394716255215664]
  This paper proposes a target-aware frequency-spatial enhancement framework with noise-resilient knowledge guidance (FSCE) for SAR target recognition.<n>The proposed framework incorporates a frequency-spatial shallow feature adaptive enhancement (DSAF) module, which processes shallow features through spatial multi-scale convolution and frequency-domain wavelet convolution.<n>Through the collaborative optimization of attention transfer and noise-resilient representation learning, the proposed approach significantly improves the stability of target recognition under noisy conditions.
  arXiv  Detail & Related papers  (2026-03-23T04:35:31Z)
• UnLoc: Leveraging Depth Uncertainties for Floorplan Localization [80.55849461031879]
  UnLoc is an efficient data-driven solution for sequential camera localization within floorplans.<n>We introduce a novel probabilistic model that incorporates uncertainty estimation, modeling depth predictions as explicit probability distributions.<n>We evaluate UnLoc on large-scale synthetic and real-world datasets, demonstrating significant improvements in terms of accuracy and robustness.
  arXiv  Detail & Related papers  (2025-09-14T14:45:43Z)
• CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability [11.076431337488973]
  This study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE network. This novel network uses CNNs and the CRATE modules to extract local and global information in images, respectively, thereby boosting learning efficiency and reducing model size.
  arXiv  Detail & Related papers  (2024-09-30T04:19:40Z)
• Self-supervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion [16.673178271652553]
  Self-supervised monocular depth estimation has received widespread attention because of its capability to train without ground truth.<n>We employ the generative-based diffusion model with a unique denoising training process for self-supervised monocular depth estimation.<n>We conduct experiments on the KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:31:20Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• Do Bayesian Neural Networks Improve Weapon System Predictive Maintenance? [0.9790236766474201]
  We implement a Bayesian inference process for Neural Networks to model the time to failure of highly reliable weapon systems. We analyze and benchmark our approach, LaplaceNN, on synthetic and real datasets.
  arXiv  Detail & Related papers  (2023-12-16T16:16:28Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• Learning Monocular Dense Depth from Events [53.078665310545745]
  Event cameras produce brightness changes in the form of a stream of asynchronous events instead of intensity frames. Recent learning-based approaches have been applied to event-based data, such as monocular depth prediction. We propose a recurrent architecture to solve this task and show significant improvement over standard feed-forward methods.
  arXiv  Detail & Related papers  (2020-10-16T12:36:23Z)
• CRAUM-Net: Contextual Recursive Attention with Uncertainty Modeling for Salient Object Detection [0.0]
  We present a novel framework that integrates multi-scale context aggregation, advanced attention mechanisms, and an uncertainty-aware module for improved SOD performance.<n>Our Adaptive Cross-Scale Context Module effectively fuses features from multiple levels, leveraging Recursive Channel Spatial Attention and Convolutional Block Attention.<n>To train our network robustly, we employ a combination of boundary-sensitive and topology-preserving loss functions, including Boundary IoU, Focal Tversky, and Topological Saliency losses.
  arXiv  Detail & Related papers  (2020-06-04T18:33:59Z)

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.