Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations

• URL: http://arxiv.org/abs/2407.18500v1
• Date: Fri, 26 Jul 2024 04:18:10 GMT
• Title: Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations
• Authors: Zipeng Wang, Yunfan Lu, Lin Wang,
• Abstract summary: This paper proposes a novel SSL event-to-video reconstruction approach, dubbed EvINR, which eliminates the need for labeled data or optical flow estimation. We use an implicit neural representation (INR), which takes in coordinate $(x, y, t)$ and predicts intensity values, to represent the event generation equation. To make EvINR feasible for online requisites, we propose several acceleration techniques that substantially expedite the training process.
• Score: 11.874972134063638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing intensity frames from event data while maintaining high temporal resolution and dynamic range is crucial for bridging the gap between event-based and frame-based computer vision. Previous approaches have depended on supervised learning on synthetic data, which lacks interpretability and risk over-fitting to the setting of the event simulator. Recently, self-supervised learning (SSL) based methods, which primarily utilize per-frame optical flow to estimate intensity via photometric constancy, has been actively investigated. However, they are vulnerable to errors in the case of inaccurate optical flow. This paper proposes a novel SSL event-to-video reconstruction approach, dubbed EvINR, which eliminates the need for labeled data or optical flow estimation. Our core idea is to reconstruct intensity frames by directly addressing the event generation model, essentially a partial differential equation (PDE) that describes how events are generated based on the time-varying brightness signals. Specifically, we utilize an implicit neural representation (INR), which takes in spatiotemporal coordinate $(x, y, t)$ and predicts intensity values, to represent the solution of the event generation equation. The INR, parameterized as a fully-connected Multi-layer Perceptron (MLP), can be optimized with its temporal derivatives supervised by events. To make EvINR feasible for online requisites, we propose several acceleration techniques that substantially expedite the training process. Comprehensive experiments demonstrate that our EvINR surpasses previous SSL methods by 38% w.r.t. Mean Squared Error (MSE) and is comparable or superior to SoTA supervised methods. Project page: https://vlislab22.github.io/EvINR/.

Related papers

• EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks [14.046487518350792]
  Spiking Neural Networks (SNNs) operate on an event-driven through sparse spike communication. We introduce Residual Potential Dropout (RPD) and Spike-Aware Training (SAT) to regulate potential distribution. Our method yields a 4.4% mAP improvement on the Gen1 dataset, while requiring 38% fewer parameters and only three time steps.
  arXiv  Detail & Related papers  (2024-03-19T09:34:11Z)
• Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement [85.66867277156089]
  We propose window-based event denoising, which simultaneously deals with a stack of events. In spatial domain, we choose maximum a posteriori (MAP) to discriminate real-world event and noise. Our algorithm can remove event noise effectively and efficiently and improve the performance of downstream tasks.
  arXiv  Detail & Related papers  (2024-02-14T15:56:42Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• 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)
• FFEINR: Flow Feature-Enhanced Implicit Neural Representation for Spatio-temporal Super-Resolution [4.577685231084759]
  This paper proposes a Feature-Enhanced Neural Implicit Representation (FFEINR) for super-resolution of flow field data. It can take full advantage of the implicit neural representation in terms of model structure and sampling resolution. The training process of FFEINR is facilitated by introducing feature enhancements for the input layer.
  arXiv  Detail & Related papers  (2023-08-24T02:28:18Z)
• Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow [18.335337530059867]
  Event cameras have gained significant traction since they open up new avenues for low-latency and low-power solutions to complex computer vision problems. To unlock these solutions, it is necessary to develop algorithms that can leverage the unique nature of event data. In this work, we propose a novel self-supervised learning pipeline for the estimation of event-based optical flow.
  arXiv  Detail & Related papers  (2023-03-09T12:37:33Z)
• Optical flow estimation from event-based cameras and spiking neural networks [0.4899818550820575]
  Event-based sensors are an excellent fit for Spiking Neural Networks (SNNs) We propose a U-Net-like SNN which, after supervised training, is able to make dense optical flow estimations. Thanks to separable convolutions, we have been able to develop a light model that can nonetheless yield reasonably accurate optical flow estimates.
  arXiv  Detail & Related papers  (2023-02-13T16:17:54Z)
• Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns [77.34726150561087]
  We introduce four complicated missing patterns, including missing and three fiber-like missing cases according to the mode-drivenn fibers. Despite nonity of the objective function in our model, we derive the optimal solutions by integrating alternating data-mputation method of multipliers.
  arXiv  Detail & Related papers  (2022-05-19T08:37:56Z)
• 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)

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.