Color Object
Color object research focuses on understanding and manipulating color information within images and other visual data, aiming to improve image processing, computer vision, and human-computer interaction. Current research emphasizes the use of deep learning models, particularly transformers and generative adversarial networks (GANs), to achieve tasks such as image colorization, color-based object recognition, and color-aware scene reconstruction. These advancements have significant implications for diverse fields, including digital image restoration, augmented reality applications for color vision deficiency, and improved performance in remote sensing and medical image analysis.
Papers
AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation
Siwei Yang, Longlong Jing, Junfei Xiao, Hang Zhao, Alan Yuille, Yingwei Li
Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer
Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada