Color Cerberus
arXiv:1907.06483v17 citations
Originality Synthesis-oriented
AI Analysis
This work addresses color constancy for image processing applications, but it is incremental as it builds on existing methods.
The paper tackled the problem of color constancy in the ISISPA competition by using a simple convolutional neural network, achieving a winning result, and noted that a partial reimplementation of a 2017 neural architecture could have performed even better.
Simple convolutional neural network was able to win ISISPA color constancy competition. Partial reimplementation of (Bianco, 2017) neural architecture would have shown even better results in this setup.