INTEL-TAU: A Color Constancy Dataset

Laakom, Firas; Raitoharju, Jenni; Iosifidis, Alexandros; Nikkanen, Jarno; Gabbouj, Moncef

doi:10.48550/arxiv.1910.10404

Cited by 3 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated the proposed method on the recently released INTEL-TAU dataset [19]. The dataset contains 7022 images in total captured using three different camera models, Canon 5DSR, Nikon D810, and Sony IMX135.…”

Section: Experiments and Discussionmentioning

confidence: 99%

Probabilistic Color Constancy

Laakom

Raitoharju

Iosifidis

et al. 2020

2020 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC). We define a framework for estimating the illumination of a scene by weighting the contribution of different image regions using a graph-based representation of the image. To estimate the weight of each (super-)pixel, we rely on two assumptions: (Super-)pixels with similar colors contribute similarly and darker (super-)pixels contribute less. The resulting system has one global optimum solution. The proposed method achieves competitive performance, compared to the state-of-the-art, on INTEL-TAU dataset.

show abstract

Section: Experiments and Discussionmentioning

confidence: 99%

Probabilistic Color Constancy

Laakom

Raitoharju

Iosifidis

et al. 2020

2020 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sensor Alignment Fine-Tuning (SAF). Besides UIP, to match the distribution of real sensors for cross-sensor evaluation, we perform a similar self-supervised method on a dataset including multiple real sensors [46]. For fine-tuning, we firstly load the network parameters from the previous step UIP for the initialization.…”

Section: Unprocessing Srgb Images For Pre-training (Uip)mentioning

confidence: 99%

Learning Enriched Illuminants for Cross and Single Sensor Color Constancy

Cun¹,

Wang²,

Pun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a certain sensor, cannot work well on others. Also, since the training datasets are collected in certain environments, the diversity of illuminants is limited for complex real world prediction. In this paper, we tackle these problems via two aspects. First, we propose cross-sensor self-supervised training to train the network. In detail, we consider both the general sRGB images and the white-balanced RAW images from current available datasets as the white-balanced agents. Then, we train the network by randomly sampling the artificial illuminants in a sensor-independent manner for scene relighting and supervision. Second, we analyze a previous cascaded framework and present a more compact and accurate model by sharing the backbone parameters with learning attention specifically. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin on cross and single sensor evaluations, respectively, with only 16% parameters of the previous best model.

show abstract

“…To evaluate the proposed approach, we use the INTEL-TAU dataset [23]. It is the largest publicly available high-resolution illumination estimation dataset with 7022 images.…”

Section: Datasetmentioning

confidence: 99%

“…Three different camera models were used, namely Canon 5DSR, Nikon D810, and Sony IMX135. We evaluate the methods using the 10-folds non-random cross-validation protocol defined in [23].…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Monte Carlo Dropout Ensembles for Robust Illumination Estimation

Laakom¹,

Raitoharju²,

Iosifidis³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Computational color constancy is a preprocessing step used in many camera systems. The main aim is to discount the effect of the illumination on the colors in the scene and restore the original colors of the objects. Recently, several deep learning-based approaches have been proposed to solve this problem and they often led to state-of-the-art performance in terms of average errors. However, for extreme samples, these methods fail and lead to high errors. In this paper, we address this limitation by proposing to aggregate different deep learning methods according to their output uncertainty. We estimate the relative uncertainty of each approach using Monte Carlo dropout and the final illumination estimate is obtained as the sum of the different model estimates weighted by the log-inverse of their corresponding uncertainties. The proposed framework leads to state-of-the-art performance on INTEL-TAU dataset.

show abstract

INTEL-TAU: A Color Constancy Dataset

Cited by 3 publications

References 13 publications

Probabilistic Color Constancy

Probabilistic Color Constancy

Learning Enriched Illuminants for Cross and Single Sensor Color Constancy

Monte Carlo Dropout Ensembles for Robust Illumination Estimation

Contact Info

Product

Resources

About