Event-guided Low-light Video Semantic Segmentation

• URL: http://arxiv.org/abs/2411.00639v1
• Date: Fri, 01 Nov 2024 14:54:34 GMT
• Title: Event-guided Low-light Video Semantic Segmentation
• Authors: Zhen Yao, Mooi Choo Chuah,
• Abstract summary: Event cameras can capture motion dynamics, filter out temporal-redundant information, and are robust to lighting conditions. We propose EVSNet, a lightweight framework that leverages event modality to guide the learning of a unified illumination-invariant representation. Specifically, we leverage a Motion Extraction Module to extract short-term and long-term temporal motions from event modality and a Motion Fusion Module to integrate image features and motion features adaptively.
• Score: 6.938849566816958
• License:
• Abstract: Recent video semantic segmentation (VSS) methods have demonstrated promising results in well-lit environments. However, their performance significantly drops in low-light scenarios due to limited visibility and reduced contextual details. In addition, unfavorable low-light conditions make it harder to incorporate temporal consistency across video frames and thus, lead to video flickering effects. Compared with conventional cameras, event cameras can capture motion dynamics, filter out temporal-redundant information, and are robust to lighting conditions. To this end, we propose EVSNet, a lightweight framework that leverages event modality to guide the learning of a unified illumination-invariant representation. Specifically, we leverage a Motion Extraction Module to extract short-term and long-term temporal motions from event modality and a Motion Fusion Module to integrate image features and motion features adaptively. Furthermore, we use a Temporal Decoder to exploit video contexts and generate segmentation predictions. Such designs in EVSNet result in a lightweight architecture while achieving SOTA performance. Experimental results on 3 large-scale datasets demonstrate our proposed EVSNet outperforms SOTA methods with up to 11x higher parameter efficiency.

Related papers

• 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)
• From Sim-to-Real: Toward General Event-based Low-light Frame Interpolation with Per-scene Optimization [29.197409507402465]
  We propose a novel per-scene optimization strategy tailored for low-light conditions. Our results demonstrate state-of-the-art performance in low-light environments.
  arXiv  Detail & Related papers  (2024-06-12T11:15:59Z)
• Motion Segmentation for Neuromorphic Aerial Surveillance [42.04157319642197]
  Event cameras offer superior temporal resolution, superior dynamic range, and minimal power requirements. Unlike traditional frame-based sensors that capture redundant information at fixed intervals, event cameras asynchronously record pixel-level brightness changes. We introduce a novel motion segmentation method that leverages self-supervised vision transformers on both event data and optical flow information.
  arXiv  Detail & Related papers  (2024-05-24T04:36:13Z)
• Event-assisted Low-Light Video Object Segmentation [47.28027938310957]
  Event cameras offer promise in enhancing object visibility and aiding VOS methods under such low-light conditions. This paper introduces a pioneering framework tailored for low-light VOS, leveraging event camera data to elevate segmentation accuracy.
  arXiv  Detail & Related papers  (2024-04-02T13:41:22Z)
• EGVD: Event-Guided Video Deraining [57.59935209162314]
  We propose an end-to-end learning-based network to unlock the potential of the event camera for video deraining. We build a real-world dataset consisting of rainy videos and temporally synchronized event streams.
  arXiv  Detail & Related papers  (2023-09-29T13:47:53Z)
• Revisiting Event-based Video Frame Interpolation [49.27404719898305]
  Dynamic vision sensors or event cameras provide rich complementary information for video frame. estimating optical flow from events is arguably more difficult than from RGB information. We propose a divide-and-conquer strategy in which event-based intermediate frame synthesis happens incrementally in multiple simplified stages.
  arXiv  Detail & Related papers  (2023-07-24T06:51:07Z)
• You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos [56.676761067861236]
  Given an untrimmed video, temporal sentence grounding aims to locate a target moment semantically according to a sentence query. Previous respectable works have made decent success, but they only focus on high-level visual features extracted from decoded frames. We propose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input.
  arXiv  Detail & Related papers  (2023-03-14T12:53:27Z)
• VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows [93.54888104118822]
  We propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task. Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios. Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods.
  arXiv  Detail & Related papers  (2021-08-11T03:55:12Z)
• EAN: Event Adaptive Network for Enhanced Action Recognition [66.81780707955852]
  We propose a unified action recognition framework to investigate the dynamic nature of video content. First, when extracting local cues, we generate the spatial-temporal kernels of dynamic-scale to adaptively fit the diverse events. Second, to accurately aggregate these cues into a global video representation, we propose to mine the interactions only among a few selected foreground objects by a Transformer.
  arXiv  Detail & Related papers  (2021-07-22T15:57:18Z)
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation [29.00635219317848]
  This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner. We also present a simple yet effective training strategy, which replaces a frame in video sequence with noises.
  arXiv  Detail & Related papers  (2020-10-19T13:08:15Z)

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.