Abstract: A method of representation learning for object detection from unlabeled point cloud sequences is described. The method includes detecting moving object traces from temporally-ordered, unlabeled point cloud sequences. The method also includes extracting a set of moving objects based on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method further includes classifying the set of moving objects extracted from on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method also includes estimating 3D bounding boxes for the set of moving objects based on the classifying of the set of moving objects.

Abstract: The manually-operated tooth-buffing tool is a dental appliance that is adapted for use with a tooth. The manually-operated tooth-buffing tool is a handheld disposable tool that is used for the buffing and polishing of the tooth. The manually-operated tooth-buffing tool comprises a buffing head and a handle. The buffing head further comprises a grit that is rubbed against the tooth such that the plaque, calculus, and stains on the tooth are removed and the surface of the tooth is smooth.

Abstract: Local histogram and local histogram-based functions can be determined by generating offset-kernel images based on domain-shifted tonal filter kernels. The offset-kernel images can be reused for multiple image locations and/or local neighborhood sizes, shapes, and weights. A neighborhood filter representing the desired local neighborhood size, shape, and frequency domain characteristics is applied to each of the offset-kernel images. Neighborhood filters may include a temporal dimension for evaluating neighborhoods in space and time. Neighborhood filtered offset-kernel images' values represent samples of local histogram or local histogram-based function corresponding with the domains of their associated domain-shifted tonal filter kernels. Arbitrary functions may be used as tonal filter kernels. A histogram kernel may be used to sample values of local histogram functions.

Abstract: Local histogram-based filters may create non-photorealistic computer graphics effects. An edge-preserving smoothing filter processes a source image to generate a smoothed image. An orientation filter processes the source image to generate a smoothed orientation image. At least one of the orientation filter and the edge-preserving smoothing filter include a local histogram-based filter. The non-photorealistic effect filter may generate a fine detail image from the smoothed image and the source image. The fine detail image may be diffused according to the smoothed orientation image to generate a brush stroke image. The brush stroke image is combined with a base image to create a non-photorealistic image. Local histogram-based filters include a closest mode, a local median, and a dominant mode filter. Local histogram-based filters are determined by convolving a neighborhood filter with one or more offset-kernel images, each based on the application of a shifted tonal filter kernel to the source image.

Abstract: Local histogram and local histogram-based functions can be determined by generating offset-kernel images based on domain-shifted tonal filter kernels. The offset-kernel images can be reused for multiple image locations and/or local neighborhood sizes, shapes, and weights. A neighborhood filter representing the desired local neighborhood size, shape, and frequency domain characteristics is applied to each of the offset-kernel images. Neighborhood filters may include a temporal dimension for evaluating neighborhoods in space and time. Neighborhood filtered offset-kernel images' values represent samples of local histogram or local histogram-based function corresponding with the domains of their associated domain-shifted tonal filter kernels. Arbitrary functions may be used as tonal filter kernels. A histogram kernel may be used to sample values of local histogram functions.

Abstract: Methods and systems of representation and manipulation of surfaces with perceptual geometric features, using a computer graphics rendering system, include executing algorithmic instructions to compute a plurality of vertices, edges and surfaces in a mesh for the purpose of defining representations of surfaces on grids. Normals and distances are determined for triangular surfaces to be considered. Additionally, height fields of a function are defined. A set of feature curves and a set of feature points are derived, based on the defined function. Infinitesimal movements along the representations of the surfaces are determined, along with derivations of properties of representations of continuous surfaces. Additional determinations of perceptual geometric features include determinations such as zero crossings, parabolic curves, flecnodes, ruffles, gutterpoints, conical points and biflecnodes in a given mesh.