Abstract: According to various embodiments, an artificial intelligence framework capable of neural synthesis of tileable textures is provided. Using a non-tileable texture input, such as single or multi-layer texture stacks, high-quality tileable textures can be generated that match the appearance of the input samples, while increasing their spatial resolution. Embodiments are provided that leverage a latent space approach in a generative network for synthesizing seamlessly tileable textures, which can maintain semantic consistency in boundaries between tiles. A tileabilty metric is provided as feedback to improve and optimize the tileability of the outout texture, for example using a sampling algorithm that can generate high-resolution, artifact-free tileable textures. In embodiments, a convolutional discriminator is provided for detecting artifacts in the synthesized textures by locally estimating the quality of the synthesized maps.

Abstract: According to various embodiments, a framework for transferring micro-scale properties of any kind (geometry, optical properties, material parameters resolution, etc.) of a material, to larger images of the same material is provided. The framework includes a machine learning model capable of learning to perform this transfer from a set of micro-scale images of one or more patches of the material and micro-scale properties of the material. The machine learning framework transfers the micro-scale properties to images of the same material, regardless of its size, resolution, illumination or geometry.

Abstract: In image segmentation it is usually assumed that all the surfaces of a scene are reflecting light in a perfectly diffuse or Lambertian manner. However, most existing surfaces are non-Lambertian surfaces. Examples of non-Lambertian surfaces are specular, glossy or mirror-like surfaces whose appearance may change depending on the point of view of the scene. The method according to an embodiment of the invention does not make the assumption that surfaces of objects in the view are perfect Lambertian reflectors by providing a surface color segmentation which takes into account the change in appearance due to the nature of the surfaces.

Abstract: According to various embodiments of the present invention, an optical capture system is provided. In one embodiment, a micro-scale optical capturing system is provided with low divergence (approximately 1°) of the incident light and low acceptance angle (<8°) of the captured light. According to embodiments, a micro-scale optical capturing system is provided with a large number of collimated high-power white LEDs as light sources, between 60 and 100 units, for example, and may be positioned at distances of about 650 mm from the sample. In one embodiment, a digital camera using 50 mm focal objective with a 25 mm length extension tube captures images of the sample. This provides a working distance of approximately 100 mm and at the same time maintains ×0.5 magnification for microscale captures, with an image size of 4×4 microns per pixel.

Abstract: In image segmentation it is usually assumed that all the surfaces of a scene are reflecting light in a perfectly diffuse or Lambertian manner. However, most existing surfaces are non-Lambertian surfaces. Examples of non-Lambertian surfaces are specular, glossy or mirror-like surfaces whose appearance may change depending on the point of view of the scene. The method according to an embodiment of the invention does not make the assumption that surfaces of objects in the view are perfect Lambertian reflectors by providing a surface color segmentation which takes into account the change in appearance due to the nature of the surfaces.

Abstract: Selecting at least one surface in a light field, such as a light field associated with multiple views corresponding to different view points of a same scene, may include displaying one of the multiple views as a reference view, selecting at least one surface in the reference view, identifying a set of pixels belonging to the selected surface, which are occluded in the reference view but visible in at least one of the multiple views, projecting the set of pixels into the reference view on the basis of a value of the pixels of the set in the view or views in which they are visible in order to form an upgraded reference view, displaying the upgraded reference view, and updating the selected surface in the upgraded reference view.

Abstract: Instead of using a single LUT to model a processing function, it is proposed to use another smaller LUT, i.e. an iterative LUT, such that, when applied at least two times in succession to data to process, the same processing function is modeled with at least the same accuracy. A specific way to compute this iterative LUT is given. Specific applications are given in the field of color processing. Modeling is more accurate and/or less bins are needed to model complex functions.

Abstract: Selecting at least one surface in a light field, such as a light field associated with multiple views corresponding to different view points of a same scene, may include displaying one of the multiple views as a reference view, selecting at least one surface in the reference view, identifying a set of pixels belonging to the selected surface, which are occluded in the reference view but visible in at least one of the multiple views, projecting the set of pixels into the reference view on the basis of a value of the pixels of the set in the view or views in which they are visible in order to form an upgraded reference view, displaying the upgraded reference view, and updating the selected surface in the upgraded reference view.