A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework

• URL: http://arxiv.org/abs/2212.07350v1
• Date: Wed, 14 Dec 2022 17:22:48 GMT
• Title: A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework
• Authors: Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego
• Abstract summary: We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. Experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches.
• Score: 13.298845944779108
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras.

Related papers

• Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions [56.84882059011291]
  We propose Deblur e-NeRF, a novel method to reconstruct blur-minimal NeRFs from motion-red events. We also introduce a novel threshold-normalized total variation loss to improve the regularization of large textureless patches.
  arXiv  Detail & Related papers  (2024-09-26T15:57:20Z)
• CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization [14.771885020122062]
  Event cameras are bio-inspired visual sensors that capture pixel-wise intensity changes and output asynchronous event streams. This paper considers the problem of rotational motion estimation using event cameras. Several event-based rotation estimation methods have been developed in the past decade, but their performance has not been evaluated.
  arXiv  Detail & Related papers  (2024-03-12T23:05:10Z)
• Graph-based Asynchronous Event Processing for Rapid Object Recognition [59.112755601918074]
  Event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes. We introduce a novel graph-based framework for event cameras, namely SlideGCN. Our approach can efficiently process data event-by-event, unlock the low latency nature of events data while still maintaining the graph's structure internally.
  arXiv  Detail & Related papers  (2023-08-28T08:59:57Z)
• EventTransAct: A video transformer-based framework for Event-camera based action recognition [52.537021302246664]
  Event cameras offer new opportunities compared to standard action recognition in RGB videos. In this study, we employ a computationally efficient model, namely the video transformer network (VTN), which initially acquires spatial embeddings per event-frame. In order to better adopt the VTN for the sparse and fine-grained nature of event data, we design Event-Contrastive Loss ($mathcalL_EC$) and event-specific augmentations.
  arXiv  Detail & Related papers  (2023-08-25T23:51:07Z)
• Event Collapse in Contrast Maximization Frameworks [13.298845944779108]
  ContrastMax (C) is a framework that provides state-of-the-art results on several event-based computer vision, tasks such as optical ego-motion or flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too few pixels. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space-time deformation.
  arXiv  Detail & Related papers  (2022-07-08T16:52:35Z)
• Lasers to Events: Automatic Extrinsic Calibration of Lidars and Event Cameras [67.84498757689776]
  This paper presents the first direct calibration method between event cameras and lidars. It removes dependencies on frame-based camera intermediaries and/or highly-accurate hand measurements.
  arXiv  Detail & Related papers  (2022-07-03T11:05:45Z)
• Globally-Optimal Contrast Maximisation for Event Cameras [30.79931004393174]
  Event cameras are bio-inspired sensors that perform well in challenging illumination with high temporal resolution. The pixels of an event camera operate independently and asynchronously. The flow of events is modelled by a general homographic warping in a space-time volume.
  arXiv  Detail & Related papers  (2022-06-10T14:06:46Z)
• Asynchronous Optimisation for Event-based Visual Odometry [53.59879499700895]
  Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. We focus on event-based visual odometry (VO) We propose an asynchronous structure-from-motion optimisation back-end.
  arXiv  Detail & Related papers  (2022-03-02T11:28:47Z)
• CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation [118.18977078626776]
  We propose an end-to-end self-supervised learning framework for event segmentation/boundary detection. Our framework exploits a transformer-based feature reconstruction scheme to detect event boundary by reconstruction errors. The goal of our work is to segment generic events rather than localize some specific ones.
  arXiv  Detail & Related papers  (2021-09-30T14:40:32Z)
• luvHarris: A Practical Corner Detector for Event-cameras [3.5097082077065]
  Event-driven computer vision has become more accessible. Current state-of-the-art have either unsatisfactory accuracy or real-time performance when considered for practical use. We present yet another method to perform corner detection, dubbed look-up event-Harris (luvHarris)
  arXiv  Detail & Related papers  (2021-05-24T17:54:06Z)

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.