A manufacturing flow of apparel such as jeans uses a laser to finish the products. The products are designed using a digital design tool, where photorealistic previews are generated in three dimensions and two dimensions. Imagery of the products are sent to retailers where customers can order the products, such as online orders. Imagery of the products are sent to factories where the products are finished. Based on the imagery, the factories make adjustments to the processes as needed so that the actual products will have an appearance as in the received imagery. As orders are received by the retailers, the factories can manufacture the desired products on demand, and the products can be delivered to customers.

This application provides a method for reconstructing a three-dimensional model, a method for training a three-dimensional reconstruction model, an apparatus, a computer device, and a storage medium. The method for reconstructing a three-dimensional model includes: obtaining an image feature coefficient of an input image; respectively obtaining, according to the image feature coefficient, a global feature map and an initial local feature map based on a texture and a shape of the input image; performing edge smoothing on the initial local feature map, to obtain a target local feature map; respectively splicing the global feature map and the target local feature map based on the texture and the shape, to obtain a target texture image and a target shape image; and performing three-dimensional model reconstruction according to the target texture image and the target shape image, to obtain a target three-dimensional model.

A method of performing anisotropic texture filtering includes generating one or more parameters describing an elliptical footprint in texture space; performing isotropic filtering at each sampling point of a set of sampling points in an ellipse to be sampled to produce a plurality of isotropic filter results, the ellipse to be sampled based on the elliptical footprint; selecting, based on one or more parameters of the set of sampling points and one or more parameters of the ellipse to be sampled, weights of an anisotropic filter that minimize a cost function that penalises high frequencies in the filter response of the anisotropic filter under a constraint that the variance of the anisotropic filter is related to an anisotropic ratio squared, the anisotropic ratio being the ratio of a major radius of the ellipse to be sampled and a minor axis of the ellipse to be sampled; and combining the plurality of isotropic filter results using the selected weights of the anisotropic filter to generate at least a portion of a filter result.

A system and a method are disclosed for varying a pixel-rate functionality of a GPU as an optional feature without an explicit implementation from within an application. User interface (UI) content may be detected in a draw call of an application and a variable-rate shader lookup map may be generated based on the detected UI content. A pixel rate of 3D content may be increased using the variable-rate shader lookup map. Additionally or alternatively, other conditions may be detected for increasing the pixel rate, such as using information in an application profile, detecting high or low luminance values, detecting motion and/or detecting temporal anti-aliasing.

Various embodiments are provided herein for tracking a user's physical environment, to facilitate on-the-fly blending of a virtual environment with detected aspects of the physical environment. Embodiments can be employed to facilitate virtual roaming by compositing virtual representations of detected physical objects into virtual environments. A computing device coupled to a HMD can select portions of a depth map generated based on the user's physical environment, to generate virtual objects that correspond to the selected portions. The computing device can composite the generated virtual objects into an existing virtual environment, such that the user can traverse the virtual environment while remaining aware of their physical environment. Among other things, the computing device can employ various blending techniques for compositing, and further provide image pass-through techniques for selective viewing of the physical environment while remaining fully-immersed in virtual reality.

A method includes generating, based on user images, a user 3-D model. The method proceeds with obtaining, via a user interface, a request to graphically represent an accessory on to a user graphical representation. This user graphical representation is generated using the user 3-D model. In response to this request, an accessory 3-D model is obtained. Further, the method includes positioning, via the user interface and based on parameters of the user 3-D model and of the accessory 3-D model, an accessory graphical representation on to the user graphical representation. The method further includes updating, in response to detecting user movement, the user 3-D model and the accessory 3-D model and presenting, via the user interface and based on these updated 3-D models, the accessory graphical representation and the user graphical representation in accordance with the user movement.

Described herein is a data processing system having a multisample antialiasing compressor coupled to a texture unit and shader execution array. In one embodiment, the data processing system includes a memory device to store a multisample render target, the multisample render target to store color data for a set of sample locations of each pixel in a set of pixels; and general-purpose graphics processor comprising a multisample antialiasing compressor to apply multisample antialiasing compression to color data generated for the set of sample locations of a first pixel in the set of pixels and a multisample render cache to store color data generated for the set of sample locations of the first pixel in the set of pixels, wherein color data evicted from the multisample render cache is to be stored to the multisample render target.

A method of and apparatus configured to perform obtaining a captured image of a real environment. The real environment includes a device having a screen. The captured image includes the device having the screen. The pose of the screen is determined based on the captured image. From a source other than the captured image, 2D content to be displayed on a representation of the screen in the virtual scene is obtained. The 2D content is projected to produce projected 2D content. The projected 2D content aligned to the pose of the screen. The virtual scene is generated as a combination of a virtual content item and the projected 2D content.

A system and method for volume rendering a light field, wherein the light field data is subjected to a layering scheme introducing a partitioning of the hogels into subsets. Each subset corresponding to a sub-volume of the layer volume, corresponds to the sub-region of the layer. Novel partitioning of the data combined with an efficient local memory caching technique, plenoptic downsampling strategies to reduce memory bandwidth requirements and volume rendering algorithm to produce a rendered light field image. A reduction in the total number of samples required can be obtained while still maintaining the quality of the resulting image. A method is also provided to order memory accesses aligned with ray calculations in order to maximize access coherency. Real-time layered scene decomposition can be combined with surface rendering method to create a hybrid real-time rendering method that supports rendering of scenes containing superimposed volumes and surfaces.

A method performed by a device for occlusion handling in augmented reality is provided. The device can generate at least one pixel classification image in a frame including an occluding object and having foreground, background, and unknown pixels. Generation of the at least one pixel classification image can include (1) calculating an initial foreground pixel probability image, and an initial background pixel probability image, and (2) calculating a normalized depth image based on depth information of the occluding object. The device can obtain an alpha mask to blend a virtual object and the foreground of the at least one pixel classification image based on determining a color of the unknown pixels. The device can render a final composition of an augmented reality image containing the virtual object occluded by the occluding object based on applying the alpha mask to pixels in the at least one pixel classification image.