This poster introduces a novel semi-automatic colorization framework which is suitable for cartoons originally shot in blackand-white on classical celluloid films. More specifically we focus especially on the cel or paper based cartoon making technology. In this case usually the background layer is a static image and only the dynamic foreground needs to be colorized frame-by-frame. We also assu...

We present here a real time mobile mapping system mounted on a vehicle. The terrestrial acquisition system is based on a geolocation system and two sensors, namely, a laser scanner and a camera with a fish-eye lens. We produce 3D colored points cloud and textured models of the environment. Once the system has been calibrated, the data acquisition and processing are done “on the way”. This artic...

Gray scale image colorization is a useful application in the world of image processing. This work presents a general technique for “colorizing” grayscale images by transferring color between a source or color image and a destination or target or grayscale image by matching luminance and texture information between the images. This technique of the gray image coloring uses a very simple algorith...

Hue Chroma Hue Chroma Hue Chroma Fig. 1: Histogram predictions. Example of predicted hue/chroma histograms. Supplementary Section 1 provides additional training and evaluation details. This is followed by more results and examples in Supplementary Section 2. To adjust the scale of the activations of layer l by factor m, without changing any other layer's activation, the weights W and the bias b...

Visual generative models, such as Generative Adversarial Networks (GANs) [1] and Variational Autoencoders (VAEs) [2], have achieve remarkable results in generating visual images [3, 4, 5, 6]. While most existing work [3, 4] focus on photorealistic images, the problem of generating artistic images is relatively underinvestigated. Different from photorealistic images, artistic images exhibit larg...

Multispectral images usually present complimentary information such as visual-band imagery and infrared imagery (near infrared or long wave infrared). There are strong evidences that the fused multispectral imagery (in gray scales) increases the reliability of interpretation (Rogers & Wood, 1990; Essock et al., 2001) and thus good for machine analysis (computer vision); whereas the colorized mu...