E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
arXiv:2206.07578 · doi:10.1109/CVPR52688.2022.01319
Abstract
Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic range (HDR), high temporal resolution, and low power consumption. However, the results of event cameras should be processed into an alternative representation for computer vision tasks. Also, they are usually noisy and cause poor performance in areas with few events. In recent years, numerous researchers have attempted to reconstruct videos from events. However, they do not provide good quality videos due to a lack of temporal information from irregular and discontinuous data. To overcome these difficulties, we introduce an E2V-SDE whose dynamics are governed in a latent space by Stochastic differential equations (SDE). Therefore, E2V-SDE can rapidly reconstruct images at arbitrary time steps and make realistic predictions on unseen data. In addition, we successfully adopted a variety of image composition techniques for improving image clarity and temporal consistency. By conducting extensive experiments on simulated and real-scene datasets, we verify that our model outperforms state-of-the-art approaches under various video reconstruction settings. In terms of image quality, the LPIPS score improves by up to 12% and the reconstruction speed is 87% higher than that of ET-Net.
arXiv admin note: This submission has been withdrawn by arXiv administrators due to inappropriate text overlap with external sources. Additional information at https://doi.org/10.1109/CVPR52688.2022.01319
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Event-based Vision: A Survey
- Score-Based Generative Modeling through Stochastic Differential Equations
- The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM
- The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception
- Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks
- A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
- Neural Jump Stochastic Differential Equations
- Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
- SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
- Stochastic Normalizing Flows
- Stochastic Differential Equations with Variational Wishart Diffusions