Generalizing Event-Based Motion Deblurring in Real-World Scenarios
- URL: http://arxiv.org/abs/2308.05932v1
- Date: Fri, 11 Aug 2023 04:27:29 GMT
- Title: Generalizing Event-Based Motion Deblurring in Real-World Scenarios
- Authors: Xiang Zhang, Lei Yu, Wen Yang, Jianzhuang Liu, Gui-Song Xia
- Abstract summary: Event-based motion deblurring has shown promising results by exploiting low-latency events.
We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur.
A two-stage self-supervised learning scheme is then developed to fit real-world data distribution.
- Score: 62.995994797897424
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Event-based motion deblurring has shown promising results by exploiting
low-latency events. However, current approaches are limited in their practical
usage, as they assume the same spatial resolution of inputs and specific
blurriness distributions. This work addresses these limitations and aims to
generalize the performance of event-based deblurring in real-world scenarios.
We propose a scale-aware network that allows flexible input spatial scales and
enables learning from different temporal scales of motion blur. A two-stage
self-supervised learning scheme is then developed to fit real-world data
distribution. By utilizing the relativity of blurriness, our approach
efficiently ensures the restored brightness and structure of latent images and
further generalizes deblurring performance to handle varying spatial and
temporal scales of motion blur in a self-distillation manner. Our method is
extensively evaluated, demonstrating remarkable performance, and we also
introduce a real-world dataset consisting of multi-scale blurry frames and
events to facilitate research in event-based deblurring.
Related papers
- Event-based Motion Deblurring via Multi-Temporal Granularity Fusion [5.58706910566768]
Event camera, a bio-inspired sensor offering continuous visual information could enhance the deblurring performance.
Existing event-based image deblurring methods usually utilize voxel-based event representations.
We introduce point cloud-based event representation into the image deblurring task and propose a Multi-Temporal Granularity Network (MTGNet)
It combines the spatially dense but temporally coarse-grained voxel-based event representation and the temporally fine-grained but spatially sparse point cloud-based event.
arXiv Detail & Related papers (2024-12-16T15:20:54Z) - Event-Based Tracking Any Point with Motion-Augmented Temporal Consistency [58.719310295870024]
This paper presents an event-based framework for tracking any point.
It tackles the challenges posed by spatial sparsity and motion sensitivity in events.
It achieves 150% faster processing with competitive model parameters.
arXiv Detail & Related papers (2024-12-02T09:13:29Z) - Implicit Event-RGBD Neural SLAM [54.74363487009845]
Implicit neural SLAM has achieved remarkable progress recently.
Existing methods face significant challenges in non-ideal scenarios.
We propose EN-SLAM, the first event-RGBD implicit neural SLAM framework.
arXiv Detail & Related papers (2023-11-18T08:48:58Z) - Adaptive Local-Component-aware Graph Convolutional Network for One-shot
Skeleton-based Action Recognition [54.23513799338309]
We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition.
Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
arXiv Detail & Related papers (2022-09-21T02:33:07Z) - Motion Deblurring with Real Events [50.441934496692376]
We propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner.
Real-world events are exploited to alleviate the performance degradation caused by data inconsistency.
arXiv Detail & Related papers (2021-09-28T13:11:44Z) - Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem
Formulation [53.850686395708905]
Event-based cameras record an asynchronous stream of per-pixel brightness changes.
In this paper, we focus on single-layer architectures for representation learning from event data.
We show improvements of up to 9 % in the recognition accuracy compared to the state-of-the-art methods.
arXiv Detail & Related papers (2020-09-23T10:40:03Z)
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.