Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams

• URL: http://arxiv.org/abs/2401.10461v2
• Date: Mon, 8 Jul 2024 08:25:47 GMT
• Title: Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams
• Authors: Liwen Hu, Ziluo Ding, Mianzhi Liu, Lei Ma, Tiejun Huang,
• Abstract summary: As a neuromorphic sensor, spike camera can generate continuous binary spike streams to capture per-pixel light intensity. We propose a bidirectional recurrent-based reconstruction framework, including a Light-Robust Representation (LR-Rep) and a fusion module. We have developed a reconstruction benchmark for high-speed low-light scenes.
• Score: 28.258022350623023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As a neuromorphic sensor with high temporal resolution, spike camera can generate continuous binary spike streams to capture per-pixel light intensity. We can use reconstruction methods to restore scene details in high-speed scenarios. However, due to limited information in spike streams, low-light scenes are difficult to effectively reconstruct. In this paper, we propose a bidirectional recurrent-based reconstruction framework, including a Light-Robust Representation (LR-Rep) and a fusion module, to better handle such extreme conditions. LR-Rep is designed to aggregate temporal information in spike streams, and a fusion module is utilized to extract temporal features. Additionally, we have developed a reconstruction benchmark for high-speed low-light scenes. Light sources in the scenes are carefully aligned to real-world conditions. Experimental results demonstrate the superiority of our method, which also generalizes well to real spike streams. Related codes and proposed datasets will be released after publication.

Related papers

• bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction [57.199618102578576]
  We propose bit2bit, a new method for reconstructing high-quality image stacks at original resolution from sparse binary quantatemporal image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data. We present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions.
  arXiv  Detail & Related papers  (2024-10-30T17:30:35Z)
• Towards Real-world Event-guided Low-light Video Enhancement and Deblurring [39.942568142125126]
  Event cameras have emerged as a promising solution for improving image quality in low-light environments. We introduce an end-to-end framework to effectively handle these tasks. Our framework incorporates a module to efficiently leverage temporal information from events and frames.
  arXiv  Detail & Related papers  (2024-08-27T09:44:54Z)
• SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams [2.609896297570564]
  We introduce Swin Spikeformer (SwinSF), a novel model for dynamic scene reconstruction from spike streams. SwinSF combines shifted window self-attention and proposed temporal spike attention, ensuring a comprehensive feature extraction. We build a new synthesized dataset for spike image reconstruction which matches the resolution of the latest spike camera.
  arXiv  Detail & Related papers  (2024-07-22T15:17:39Z)
• An Asynchronous Linear Filter Architecture for Hybrid Event-Frame Cameras [9.69495347826584]
  We present an asynchronous linear filter architecture, fusing event and frame camera data, for HDR video reconstruction and spatial convolution. The proposed AKF pipeline outperforms other state-of-the-art methods in both absolute intensity error (69.4% reduction) and image similarity indexes (average 35.5% improvement)
  arXiv  Detail & Related papers  (2023-09-03T12:37:59Z)
• Recurrent Spike-based Image Restoration under General Illumination [21.630646894529065]
  Spike camera is a new type of bio-inspired vision sensor that records light intensity in the form of a spike array with high temporal resolution (20,000 Hz) Existing spike-based approaches typically assume that the scenes are with sufficient light intensity, which is usually unavailable in many real-world scenarios such as rainy days or dusk scenes. We propose a Recurrent Spike-based Image Restoration (RSIR) network, which is the first work towards restoring clear images from spike arrays under general illumination.
  arXiv  Detail & Related papers  (2023-08-06T04:24:28Z)
• Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video [111.08121952640766]
  This paper presents a novel deep-learning based solution to the RS temporal super-resolution problem. By leveraging the multi-view geometry relationship of the RS imaging process, our framework successfully achieves high framerate GS generation. Our method can produce high-quality GS image sequences with rich details, outperforming the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-06T16:47:12Z)
• HDR Reconstruction from Bracketed Exposures and Events [12.565039752529797]
  Reconstruction of high-quality HDR images is at the core of modern computational photography. We present a multi-modal end-to-end learning-based HDR imaging system that fuses bracketed images and event in the feature domain. Our framework exploits the higher temporal resolution of events by sub-sampling the input event streams using a sliding window.
  arXiv  Detail & Related papers  (2022-03-28T15:04:41Z)
• Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding [87.5799910153545]
  Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Blind Motion Deblurring Super-Reslution Networks is proposed to learn dynamic-temporal information from single static motion-blurred images.
  arXiv  Detail & Related papers  (2021-05-27T11:52:45Z)
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution [100.11355888909102]
  Space-time video super-resolution aims at generating a high-resolution (HR) slow-motion video from a low-resolution (LR) and low frame rate (LFR) video sequence. We present a one-stage space-time video super-resolution framework, which can directly reconstruct an HR slow-motion video sequence from an input LR and LFR video.
  arXiv  Detail & Related papers  (2021-04-15T17:59:23Z)
• EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning [75.17497166510083]
  Event cameras sense intensity changes and have many advantages over conventional cameras. Some methods have been proposed to reconstruct intensity images from event streams. The outputs are still in low resolution (LR), noisy, and unrealistic. We propose a novel end-to-end pipeline that reconstructs LR images from event streams, enhances the image qualities and upsamples the enhanced images, called EventSR.
  arXiv  Detail & Related papers  (2020-03-17T10:58:10Z)
• Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution [95.26202278535543]
  A simple solution is to split it into two sub-tasks: video frame (VFI) and video super-resolution (VSR) temporalsynthesis and spatial super-resolution are intra-related in this task. We propose a one-stage space-time video super-resolution framework, which directly synthesizes an HR slow-motion video from an LFR, LR video.
  arXiv  Detail & Related papers  (2020-02-26T16:59:48Z)

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.