paper-with-me

Papers

FC4: Fully Convolutional Color Constancy With Confidence-Weighted Pooling

2017-07-01 · CVPR 2017 7 · Yuanming Hu, Baoyuan Wang, Stephen Lin

Improvements in color constancy have arisen from the use of convolutional neural networks (CNNs). However, the patch-based CNNs that exist for this problem are faced with the issue of estimation ambiguity, where a patch may contain insufficient information to establish a unique or even a limited possible range of illumination colors. Image patches with estimation ambiguity not only appear with great frequency in photographs, but also significantly degrade the quality of network training and inference. To overcome this problem, we present a fully convolutional network architecture in which patches throughout an image can carry different confidence weights according to the value they provide for color constancy estimation. These confidence weights are learned and applied within a novel pooling layer where the local estimates are merged into a global solution. With this formulation, the network is able to determine "what to learn" and "how to pool" automatically from color constancy datasets without additional supervision. The proposed network also allows for end-to-end training, and achieves higher efficiency and accuracy. On standard benchmarks, our network outperforms the previous state-of-the-art while achieving 120x greater efficiency.

📄 PDF Abstract BibTeX

Code (1)

yuanming-hu/fc4 tf

Tasks

Color Constancy

Similar Papers 제목 키워드 기반

Cascading Convolutional Color Constancy

2019-12-24 · Huanglin Yu, Ke Chen, Kaiqi Wang, Yanlin Qian 외

Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy. However, it's still challenging due to intrinsic appearance and label ambiguiti…

Color Constancy

Cross-Camera Convolutional Color Constancy

2020-11-24 · ICCV 2021 10 · Mahmoud Afifi, Jonathan T. Barron, Chloe LeGendre, Yun-Ta Tsai 외

We present "Cross-Camera Convolutional Color Constancy" (C5), a learning-based method, trained on images from multiple cameras, that accurately estimates a scene's illuminant color from raw images captured by a new camer…

Color ConstancyCPUGPU

Convolutional Color Constancy

2015-07-02 · ICCV 2015 12 · Jonathan T. Barron

Color constancy is the problem of inferring the color of the light that illuminated a scene, usually so that the illumination color can be removed. Because this problem is underconstrained, it is often solved by modeling…

Color Constancyobject-detectionObject DetectionStructured Prediction

Recurrent Color Constancy

2017-10-01 · ICCV 2017 10 · Yanlin Qian, Ke Chen, Jarno Nikkanen, Joni-Kristian Kamarainen 외

We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated. We propose an end-to-end trainable recurrent color constancy network -…

Color Constancy

Color Constancy Convolutional Autoencoder

2019-06-04 · Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen 외

In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem. We propose two novel approaches based on convolutional autoencoders: an unsupervised pre-training a…

Color ConstancyUnsupervised Pre-training