Learning to See Moving Objects in the Dark

Jiang, Haiyang; Zheng, Yinqiang

doi:10.1109/iccv.2019.00742

Cited by 98 publications

(51 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, these methods can achieve good results in their assumed conditions, while a comprehensive model to capture all degradation and handle the corresponding degradation is still absent. Besides, there are works (Chen et al , 2019Jiang and Zheng 2019) considering the application scenario to obtain enhanced images from raw images (un-processing images). The datasets of raw short-exposure low-light images and the corresponding raw long-exposure reference images are introduced and novel end-to-end trainable pipelines for processing low-light images/videos are designed.…”

Section: Multi-exposed Resultsmentioning

confidence: 99%

Benchmarking Low-Light Image Enhancement and Beyond

et al. 2021

View full text Add to dashboard Cite

In this paper, we present a systematic review and evaluation of existing single-image low-light enhancement algorithms. Besides the commonly used low-level vision oriented evaluations, we additionally consider measuring machine vision performance in the low-light condition via face detection task to explore the potential of joint optimization of high-level and low-level vision enhancement. To this end, we first propose a large-scale low-light image dataset serving both low/high-level vision with diversified scenes and contents as well as complex degradation in real scenarios, called Vision Enhancement in the LOw-Light condition (VE-LOL). Beyond paired low/normal-light images without annotations, we additionally include the analysis resource related to human, i.e. face images in the low-light condition with annotated face bounding boxes. Then, efforts are made on benchmarking from the perspective of both human and machine visions. A rich variety of criteria is used for the low-level vision evaluation, including full-reference, no-reference, and semantic similarity metrics. We also measure the effects of the low-light enhancement on face detection in the low-light condition. State-of-the-art face detection methods are used in the evaluation. Furthermore, with the rich material of VE-LOL, we explore the novel problem of joint low-light enhancement and face detection. We develop an enhanced face detector to apply low-light enhancement and face detection jointly. The features extracted by the enhancement module are fed to the successive layer with the same resolution of the detection module. Thus, these features are intertwined together to unitedly learn useful information across two phases, i.e. enhancement and detection. Experiments on VE-LOL provide a comparison of state-of-the-art low-light enhancement algorithms, point out their limitations, and suggest promising future directions. Our dataset has supported the Track "Face Detection in Low Light Conditions" of CVPR UG2+ Challenge (2019-2020) (http://cvpr2020.ug2challenge.org/).

show abstract

Section: Multi-exposed Resultsmentioning

confidence: 99%

Benchmarking Low-Light Image Enhancement and Beyond

et al. 2021

View full text Add to dashboard Cite

show abstract

“…More recently, such an enhancement task has been expanded to the video domain. New datasets include DRV [2] and SMOID [8]. Although both datasets contain dark videos, their focus is more towards enhancing the visibility of video frames.…”

Section: Dark Visual Datasetsmentioning

confidence: 99%

ARID: A New Dataset for Recognizing Action in the Dark

Yang

Cao

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

The task of action recognition in dark videos is useful in various scenarios, e.g., night surveillance and self-driving at night. Though progress has been made in action recognition task for videos in normal illumination, few have studied action recognition in the dark, partly due to the lack of sufficient datasets for such a task. In this paper, we explored the task of action recognition in dark videos. We bridge the gap of the lack of data by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset. It consists of 3,784 video clips with 11 action categories. To the best of our knowledge, it is the first dataset focused on human actions in dark videos. To gain further understanding of our ARID dataset, we analyze our dataset in detail and showed its necessity over synthetic dark videos. Additionally, we benchmark the performance of current action recognition models on our dataset and explored potential methods for increasing their performances. We show that current action recognition models and frame enhancement methods may not be effective solutions for the task of action recognition in dark videos (data available at https://xuyu0010.github.io/arid).

show abstract

“…A precise pixel-to-pixel alignment is also required to fuse these two images, which is problematic at very low light levels. More recent approaches tackle the low-light imaging problem using modern neural network models on either processed images by Image Signal Processors (ISPs) [29] or directly on raw sensor data [6,5,19]. Among them, processing on raw data has distinct advantages owing to the reduced quantization error and higher dynamic range.…”

Section: Related Workmentioning

confidence: 99%