Flash Lightens Gray Pixe

Qian, Yong Zhong; Yan, Song; Kämäräinen, Joni-Kristian; Matas, Jiřı́

doi:10.1109/icip.2019.8803468

Cited by 6 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their approach existing CC methods can be used and illuminant is estimated from multiple frames of a same scene where scene boundaries are automatically detected. Yoo et al [18] propose a color constancy algorithm for AC bulb illuminated (indoor) scenes using a high-speed camera and Qian et al [19] for a pair of images with and without flash. However, the seminal work of temporal color constancy is Qian et al [9] who seeded the term and proposed a temporal CC algorithm using semantic AlexNet features and a Long Short Term Memory (LSTM) recurrent neural network to process sequential input frames.…”

Section: Related Workmentioning

confidence: 99%

A Benchmark for Burst Color Constancy

Qian

Käpylä

Kämäräinen

et al. 2020

Computer Vision – ECCV 2020 Workshops

Self Cite

View full text Add to dashboard Cite

Temporal Color Constancy (CC) is a recently proposed approach that challenges the conventional single-frame color constancy. The conventional approach is to use a single frame -shot frame -to estimate the scene illumination color. In temporal CC, multiple frames from the view finder sequence are used to estimate the color. However, there are no realistic large scale temporal color constancy datasets for method evaluation. In this work, a new temporal CC benchmark is introduced. The benchmark comprises of (1) 600 real-world sequences recorded with a high-resolution mobile phone camera, (2) a fixed train-test split which ensures consistent evaluation, and (3) a baseline method which achieves high accuracy in the new benchmark and the dataset used in previous works. Results for more than 20 well-known color constancy methods including the recent state-of-the-arts are reported in our experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

A Benchmark for Burst Color Constancy

Qian

Käpylä

Kämäräinen

et al. 2020

Computer Vision – ECCV 2020 Workshops

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast with the plethora of methods for CCC targeting single images, few attempts have been made to deal with sequences of frames (i.e., with the temporal task). Research on TCC so far has either focused on some special cases (e.g., Yoo and Kim 19 targeted AC bulb illuminated scenes and Qian et al 20 paired images with and without flash), or made strong assumptions, such as constant illumination across frames. 21,22 There have been only a few attempts that we are aware of devising more general-purpose neural strategies.…”

Section: Related Workmentioning

confidence: 99%

Cascading convolutional temporal color constancy

et al. 2023

View full text Add to dashboard Cite

Computational color constancy (CCC) consists of computing color estimates of the ambient scene illumination and using them to remove unwanted chromatic distortions. Much research has focused on illuminant estimation for CCC on single images, with few attempts of leveraging the temporal information intrinsic in sequences of correlated images (e.g., the frames in a video), a task known as temporal color constancy (TCC). The state-of-the-art for TCC is temporal color constancy network (TCCNet), a deep-learning architecture that uses a convolutional long short-term memory network for aggregating the encodings produced by convolutional neural network submodules for each image in a sequence. We extend this architecture with different models obtained by (i) substituting the TCCNet submodules with cascading convolutional color constancy (C4), the state-of-the-art method for CCC targeting images and (ii) adding a cascading strategy to perform an iterative improvement of the estimate of the illuminant. We tested our models on the recently released TCC benchmark and achieved results that surpass the state-of-the-art. Analyzing the impact of the number of frames involved in illuminant estimation on performance, we show that it is possible to reduce inference time by training the models on a few selected frames from the sequences while retaining comparable accuracy.

show abstract

“…In contrast with the plethora of methods for CCC targeting single images, few attempts have been made to deal with sequences of frames (i.e., with the temporal task). Research on TCC so far has either focused on some special cases (e.g., [28] target AC bulb illuminated scenes and [20] pairs of images with and without flash), or made strong assumptions such as constant illumination across frames [26,17]. There have been only a few attempts that we are aware of devising more general-purpose neural strategies [1,18,19].…”

Section: Related Workmentioning

confidence: 99%

Cascading Convolutional Temporal Colour Constancy

Rizzo,

Conati,

Jang

et al. 2021

Preprint

View full text Add to dashboard Cite

Computational Colour Constancy (CCC) consists of estimating the colour of one or more illuminants in a scene and using them to remove unwanted chromatic distortions. Much research has focused on illuminant estimation for CCC on single images, with few attempts of leveraging the temporal information intrinsic in sequences of correlated images (e.g., the frames in a video), a task known as Temporal Colour Constancy (TCC). The state-of-the-art for TCC is TCCNet, a deep-learning architecture that uses a ConvL-STM for aggregating the encodings produced by CNN submodules for each image in a sequence. We extend this architecture with different models obtained by (i) substituting the TCCNet submodules with C4, the state-of-the-art method for CCC targeting images; (ii) adding a cascading strategy to perform an iterative improvement of the estimate of the illuminant. We tested our models on the recently released TCC benchmark and achieved results that surpass the stateof-the-art. Analyzing the impact of the number of frames involved in illuminant estimation on performance, we show that it is possible to reduce inference time by training the models on few selected frames from the sequences while retaining comparable accuracy.

show abstract

Flash Lightens Gray Pixe

Cited by 6 publications

References 21 publications

A Benchmark for Burst Color Constancy

A Benchmark for Burst Color Constancy

Cascading convolutional temporal color constancy

Cascading Convolutional Temporal Colour Constancy

Contact Info

Product

Resources

About