Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: System and method for an active learning system including a sensor obtains data from a scene including a set of images having objects. A memory to store active learning data including an object detector trained for detecting objects in images. A processor in communication with the memory, is configured to detect a semantic class and a location of at least one object in an image selected from the set of images using the object detector to produce a detection metric as a combination of an uncertainty of the object detector about the semantic class of the object in the image (classification) and an uncertainty of the object detector about the location of the object in the image (localization). Using an output interface or a display type device, in communication with the processor, to display the image for human labeling when the detection metric is above a threshold.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: System and method for an active learning system including a sensor obtains data from a scene including a set of images having objects. A memory to store active learning data including an object detector trained for detecting objects in images. A processor in communication with the memory, is configured to detect a semantic class and a location of at least one object in an image selected from the set of images using the object detector to produce a detection metric as a combination of an uncertainty of the object detector about the semantic class of the object in the image (classification) and an uncertainty of the object detector about the location of the object in the image (localization). Using an output interface or a display type device, in communication with the processor, to display the image for human labeling when the detection metric is above a threshold.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: A method of rendering an image includes Monte Carlo rendering a scene to produce a noisy image. The noisy image is processed to render an output image. The processing applies a machine learning model that utilizes colors and/or features from the rendering system for denoising the noisy image and/or to for adaptively placing samples during rendering.

Abstract: Apparatus and methods comprise examination of a subject using images of the subject. The images can provide a non-invasive analysis technique and can include a plurality of images of a portion of the subject at different times a temperature stimulus applied to the subject. An image of the portion of the subject can be aligned such that each pixel of the image corresponds to the same point on the subject over a sequence of images of the portion. The sequence of images can be processed after aligning the images such that data is extracted from the images. The extracted data can be used to make decisions regarding the health status of the subject. Additional apparatus, systems, and methods are disclosed.

Abstract: Apparatus and methods comprise examination of a subject using images of the subject. The images can provide a non-invasive analysis technique and can include a plurality of images of a portion of the subject at different times a temperature stimulus applied to the subject. An image of the portion of the subject can be aligned such that each pixel of the image corresponds to the same point on the subject over a sequence of images of the portion. The sequence of images can be processed after aligning the images such that data is extracted from the images. The extracted data can be used to make decisions regarding the health status of the subject. Additional apparatus, systems, and methods are disclosed.

Abstract: A method of producing noise-free images is disclosed. The method includes using machine learning incorporating a filter to output filter parameters using the training images. The machine learning may include training a neural network. The filter parameters are applied to Monte Carlo rendered training images that have noise to generate noise-free images. The training may include determining, computing and extracting features of the training images; computing filter parameters; applying an error metric; and applying backpropgation. The neural network may be a multilayer perceptron. The machine learning model is applied to new noisy Monte Carlo rendered images to create noise-free images. This may include applying the filter to the noisy Monte Carlo rendered images using the filter parameters to create the noise-free images.

Abstract: Apparatus and methods comprise examination of a subject using images of the subject. The images can provide a non-invasive analysis technique and can include a plurality of images of a portion of the subject at different times a temperature stimulus applied to the subject. An image of the portion of the subject can be aligned such that each pixel of the image corresponds to the same point on the subject over a sequence of images of the portion. The sequence of images can be processed after aligning the images such that data is extracted from the images. The extracted data can be used to make decisions regarding the health status of the subject. Additional apparatus, systems, and methods are disclosed.

Abstract: A system and methods for building a map non-invasively (i.e. mapping of occluded and non-occluded obstacles) based on a small number of wireless channel measurements. Approaches for building an obstacle map are based on coordinated space, random space and frequency sampling, such that the sparse representation of the map in space, wavelet or spatial variations, are exploited in order to build the map with minimal sensing.

Abstract: The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.

Abstract: Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A{circumflex over (x)} produces higher-quality rendering with less samples than previous approaches. A filter formulation ? makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).

Abstract: The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.

Abstract: Exemplary embodiments provide microscope devices and methods for forming and using the microscope devices. The microscope device can include a light emitter array with each light emitter individually addressable to either emit or detect light signals. Magnified images of a sample object can be generated by a reflection mechanism and/or a transmission mechanism using one or more microscope devices in an imaging system. Real-time computer control of which microscope pixels are viewed can allow the user to digitally replicate the “fovea” function of human vision. Viewing an object from both sides in the double-sided microscope system and from multiple pixel positions can allow the microscope to reconstruct pseudo-3D images of the object.

Abstract: Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A?x produces higher-quality rendering with less samples than previous approaches. A filter formulation ? makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).

Abstract: A method for computer graphics rendering system uses a silhouette map containing boundary position information that is used to reconstruct precise boundaries in the rendered image, even under high magnification. In one embodiment the silhouette map is used together with a depth map to precisely render the edges of shadows. In another embodiment, the silhouette map is used together with a bitmap texture to precisely render the borders between differently colored regions of the bitmap. The technique may be implemented in software, on programmable graphics hardware in real-time, or with custom hardware.

Abstract: The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.