Abstract: A method renders a model of an object by first acquiring, in an acquisition space, a reflectance field of the object. The reflectance field includes a set of reflectance images of the object and a point model of the object. The model is deformed in an object space to generate a deformed model. For each point of the deformed model in the object space, the set of the reflectance images is queried in the acquisition space to obtain reflectance coefficients for each point. Each point of the deformed model is then shaded according to the corresponding reflectance coefficients to generate an image of the object reflecting the deforming.

Abstract: A method and system estimates a reflectance function of an arbitrary scene. The scene is illuminated under various lighting condition. For each lighting condition there is an associated illumination image and an observed image. Multiple, non-overlapping kernels are determined for each pixel in a reflectance image from the pairs of illumination and observed images. A weight is then determined for each kernel to estimate the reflectance function represented as the reflectance image.

Abstract: A three-dimensional television system includes an acquisition stage, a display stage and a transmission network. The acquisition stage includes multiple video cameras configured to acquire input videos of a dynamically changing scene in real-time. The display stage includes a three-dimensional display unit configured to concurrently display output videos generated from the input videos. The transmission network connects the acquisition stage to the display stage.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A system encodes videos acquired of a moving object in a scene by multiple fixed cameras. Camera calibration data of each camera are first determined. The camera calibration data of each camera are associated with the corresponding video. A segmentation mask for each frame of each video is determined. The segmentation mask identifies only foreground pixels in the frame associated with the object. A shape encoder then encodes the segmentation masks, a position encoder encodes a position of each pixel, and a color encoder encodes a color of each pixel. The encoded data can be combined into a single bitstream and transferred to a decoder. At the decoder, the bitstream is decoded to an output video having an arbitrary user selected viewpoint. A dynamic 3D point model defines a geometry of the moving object. Splat sizes and surface normals used during the rendering can be explicitly determined by the encoder, or explicitly by the decoder.

Abstract: A method determines an optimal set of viewpoints to acquire a 3D shape of a face. A view-sphere is tessellated with a plurality of viewpoint cells. The face is at an approximate center of the view-sphere. Selected viewpoint cells are discarded. The remaining viewpoint cells are clustered to a predetermined number of viewpoint cells according to a silhouette difference metric. The predetermined number of viewpoint cells are searched for a set of optimal viewpoint cells to construct a 3D model of the face.

Abstract: A method reconstructs or synthesizes heads from 3D models of heads and 2D silhouettes of heads. A 3D statistical model is generated from multiple real human heads. The 3D statistical model includes a model parameter in the form of basis vectors and corresponding coefficients. Multiple 2D silhouettes of a particular head are acquired using a camera for example. The 3D statistical model is fitted to multiple 2D silhouettes to determine a particular value of the model parameter corresponding to the plurality of 2D silhouettes. Then, the 3D statistical model is rendered according to the particular value of the model parameter to reconstruct the particular head.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A method models a three-dimensional object with a compressed surface reflectance field. Images of the object are acquired with multiple cameras for multiple viewpoints under different lighting conditions. The images are stored in a matrix Mr representing a surface reflectance field for the three-dimensional object. The matrix Mr is factorized into principle components pck and coefficients cfk. The principal components pck are stored in a matrix Mpc. The matrix Mpc is then factorized into principle components pcm and coefficients cfk which can be stored for each vertex V of a model of the three-dimensional object. The corresponding values of the principle components pcm, coefficients cfk, and coefficients cfk, respectively represent a compression of a surface map, which can be rendered from arbitrary viewpoints and under arbitrary lighting conditions.

Abstract: A method constructs three-dimensional (3D) models of a scene from a set of two-dimensional (2D) input images. The 3D model can then be used to reconstruct the scene from arbitrary viewpoints.

Abstract: A system digitizes a three-dimensional object as a three-dimension model by placing the object on a turntable while taking two sets of corresponding images. The first set of images and the second set of images are obtained while rotating the turntable to a various positions and illuminated the object with the overhead lights and backlights. There is a one to one correspondence for images in each set for each position of the turntable. Object shape data and texture data are respectively extracted from the first and second set of images. The object shape data is correlated with the object texture data to construct the three-dimensional digital model stored in a memory of a computer system.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A method renders a model of a 3D object. A polygon model of the 3D object is generated, and a set of input images are acquired of the object. For each vertex of the polygon model, a set of visible views are located, and a set of closest views are selected from the visibility views. Blending weights are determined for each closest view. Then, the each polygon in the model is rendered into an output image. The rendering is performed by blending images of the set of input images corresponding to the set of closest views of each vertex of the polygon using the blending weights.

Abstract: A method produces an image from a set of discrete sample points. The sample points can define a 3D volume or surface. Each discrete sample point is projected to a screen space. A continuous resampling filter for each sample point is generated in screen space. The continuous resampling filter is a combination of a continuous reconstruction function and a continuous filter function for the sample point in screen space. The continuous resampling filter is then applied to each corresponding discrete sample in the screen space to generate a continuous sample for the image. The continuous samples can be rasterized to pixels using any known rasterization process or method.

Abstract: A method renders a 3D model of a graphics object wherein the model includes discrete zero-dimensional points. A first opaque polygon is centered on each point, and the polygon is rendered to obtain depth values of a depth image in a z-buffer. A second polygon is centered on each point. The second polygons are adapted to associated object space EWA resampling filters, and the adapted second polygons are rendered as an image according to the depth values in the depth image.

Abstract: A method models a three-dimensional object with a compressed surface reflectance field. Images of the object are acquired with multiple cameras for multiple viewpoints under different lighting conditions. The images are stored in a matrix Mr representing a surface reflectance field for the three-dimensional object. The matrix Mr is factorized into principle components pck and coefficients cfk. The principal components pck are stored in a matrix Mpc. The matrix Mpc is then factorized into principle components pcm and coefficients cfk which can be stored for each vertex V of a model of the three-dimensional object. The corresponding values of the principle components pcm, coefficients cfk, and coefficients cfk, respectively represent a compression of a surface map, which can be rendered from arbitrary viewpoints and under arbitrary lighting conditions.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: A method models a three-dimensional object by first acquiring alpha mattes of the object for multiple viewpoints. The alpha mattes are then projected onto a surface hull completely enclosing the object to construct an opacity hull storing opacity values of the surface of the object. The object is illuminated for various lighting conditions while images are acquired. The images are projected onto the opacity hull to render the object under arbitrary lighting conditions for arbitrary viewpoints.

Abstract: In a method for projecting surface points of a graphic object onto pixels in a depth buffer to determine depth values of the pixels, each surface point is projected onto a corresponding pixels. A depth value of each projected surface point is stored in the pixel only if the depth value of the projected surface point is less than the depth value of the pixel. A tangential disk is constructed at a position of the surface point, the tangential disk has a radius larger than a maximum distance between the surface points. The tangential disk is projected onto a corresponding subset of the pixels. Depth values of the projected tangential disk are stored in the corresponding subsets of pixels only if the depth values of the projected tangential disk are less than the depth values of the corresponding subsets of pixels.