Abstract: Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.

Abstract: A technique for rendering an input geometry includes generating a first segmentation mask for a first input geometry and a first set of texture maps associated with one or more portions of the first input geometry. The technique also includes generating, via one or more neural networks, a first set of neural textures for the one or more portions of the first input geometry. The technique further includes rendering a first image corresponding to the first input geometry based on the first segmentation mask, the first set of texture maps, and the first set of neural textures.

Abstract: Embodiments herein describe a host that polls a network adapter to receive data from a network. That is, the host/CPU/application thread polls the network adapter (e.g., the network card, NIC, or SmartNIC) to determine whether a packet has been received. If so, the host informs the network adapter to store the packet (or a portion of the packet) in a CPU register. If the requested data has not yet been received by the network adapter from the network, the network adapter can delay the responding to the request to provide extra time for the adapter to receive the data from the network.

Abstract: A technique for synthesizing a shape includes generating a first plurality of offset tokens based on a first shape code and a first plurality of position tokens, wherein the first shape code represents a variation of a canonical shape, and wherein the first plurality of position tokens represent a first plurality of positions on the canonical shape. The technique also includes generating a first plurality of offsets associated with the first plurality of positions on the canonical shape based on the first plurality of offset tokens. The technique further includes generating the shape based on the first plurality of offsets and the first plurality of positions.

Abstract: One embodiment of the present invention sets forth a technique for performing appearance capture. The technique includes receiving a first sequence of images of an object, wherein the first sequence of images includes a first set of images interleaved with a second set of images, and wherein the first set of images is captured based on illumination of the object using a first lighting pattern and the second set of images is captured based on illumination of the object using one or more lighting patterns that are different from the first lighting pattern. The technique also includes generating a first set of appearance parameters associated with the object based on a first inverse rendering associated with the first sequence of images.

Abstract: The present invention sets forth a technique for simulating wrinkles under dynamic facial expression. The technique includes receiving a wrinkle graph, including a plurality of nodes associated with a plurality of pores included in a three-dimensional (3D) representation of a facial structure and a plurality of edges associated with a plurality of wrinkles included in the 3D representation of a facial structure. The technique also includes assigning one or more of the plurality of wrinkles associated with edges in the wrinkle graph to one of a plurality of bins and generating, for each of the bins, a plurality of pre-computed displacement texture maps. The technique further includes generating a per-frame displacement texture map and modifying an animation frame based on the per-frame displacement texture map, such that the modified animation frame depicts the plurality of pores and the plurality of wrinkles included in the 3D representation of the facial structure.

Abstract: A network interface device comprises a streaming data processing path comprising a first data processing engine and hubs. A first scheduler associated with a first hub controls an output of data by the first hub to the first data processing engine and a second scheduler associated with a second hub controls an output of data by the second hub. The first hub is arranged upstream of the first data processing engine on the data processing path and is configured to receive data from a first upstream data path entity and from a first data processing entity implemented in programmable circuitry via a data ingress interface of the first hub. The first data processing engine is configured to receive data from the first hub, process the received data and output the processed data to the second hub arranged downstream of first data processing engine.

Abstract: The present invention sets forth a technique for simulating wrinkles under dynamic facial expression. This technique includes sampling a plurality of nodes from a three-dimensional (3D) representation of a facial structure, wherein each node represents a pore in the facial structure. The technique also generates one or more edges, with each of the one or more edges connecting a node of the plurality of nodes to a different node selected from the plurality of nodes. The technique further generates a wrinkle graph comprising the plurality of nodes, the one or more edges, and a plurality of edge weights associated with the edges included in the wrinkle graph. The technique may also modify the 3D representation of the facial structure based on the wrinkle graph and one or more dynamic expressions associated with the 3D representation.

Abstract: A computing device, including a hardware accelerator configured to receive a first matrix and receive a second matrix. The hardware accelerator may, for a plurality of partial matrix regions, in a first iteration, read a first submatrix of the first matrix and a second submatrix of the second matrix into a front-end processing area. The hardware accelerator may multiply the first submatrix by the second submatrix to compute a first intermediate partial matrix. In each of one or more subsequent iterations, the hardware accelerator may read an additional submatrix into the front end processing area. The hardware accelerator may compute an additional intermediate partial matrix as a product of the additional submatrix and a submatrix reused from an immediately prior iteration. The hardware accelerator may compute each partial matrix as a sum of two or more of the intermediate partial matrices and may output the plurality of partial matrices.

Abstract: Some implementations of the disclosure are directed to capturing facial training data for one or more subjects, the captured facial training data including each of the one or more subject's facial skin geometry tracked over a plurality of times and the subject's corresponding jaw poses for each of those plurality of times; and using the captured facial training data to create a model that provides a mapping from skin motion to jaw motion. Additional implementations of the disclosure are directed to determining a facial skin geometry of a subject; using a model that provides a mapping from skin motion to jaw motion to predict a motion of the subject's jaw from a rest pose given the facial skin geometry; and determining a jaw pose of the subject using the predicted motion of the subject's jaw.

Abstract: Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.

Abstract: One embodiment of the present invention sets forth a technique for evaluating three-dimensional (3D) reconstructions. The technique includes generating a 3D reconstruction of an object based on one or more mesh parameters. The technique also includes generating, based on the 3D reconstruction, a 3D rendering of the object. The technique further includes generating, using a machine learning model, a perceptual score associated with the 3D rendering and an input image of the object. The generated score represents how closely the 3D rendering matches the input image.

Abstract: One embodiment of the present invention sets forth a technique for performing appearance capture. The technique includes receiving a first sequence of images of an object, wherein the first sequence of images includes a first set of images interleaved with a second set of images, and wherein the first set of images is captured based on illumination of the object using a first lighting pattern and the second set of images is captured based on illumination of the object using one or more lighting patterns that are different from the first lighting pattern. The technique also includes generating a first set of appearance parameters associated with the object based on a first inverse rendering associated with the first sequence of images.

Abstract: One embodiment of the present invention sets forth a technique for retargeting a facial expression to a different facial identity. The technique includes generating, based on an input target facial identity, a facial identity code in an input identity latent space. The technique further includes converting a spatial input point from an input facial identity space of the input target facial identity to a canonical-space point in a canonical space. The technique still further includes generating one or more canonical simulator control values based on the facial identity code, an input source facial expression, and the canonical-space point. The technique still further includes generating a simulated active soft body based on one or more identity-specific control values, wherein each identity-specific control value corresponds to one or more of the canonical simulator control values and is in an output facial identity space associated with an output target facial identity.

Abstract: A network interface device comprises at least one processor configured to validate at least a part of a context associated with a queue pair, the context being fetched from a memory on a host device.

Abstract: A network interface device comprises circuitry to add a frame check sequence value a data packet to be transmitted onto a network. The data packet with the frame check sequence value is stored in memory. Media access control layer circuitry reads the data packet from the memory and determines if the frame check sequence value is correct. When it is note correct, it is determined that the data in the data packet is corrupted.

Abstract: Techniques are disclosed for capturing facial appearance properties. In some examples, a facial capture system includes light source(s) that produce linearly polarized light, at least one camera that is cross-polarized with respect to the polarization of light produced by the light source(s), and at least one other camera that is not cross-polarized with respect to the polarization of the light produced by the light source(s). Images captured by the cross-polarized camera(s) are used to determine facial appearance properties other than specular intensity, such as diffuse albedo, while images captured by the camera(s) that are not cross-polarized are used to determine facial appearance properties including specular intensity. In addition, a coarse-to-fine optimization procedure is disclosed for determining appearance and detailed geometry maps based on images captured by the cross-polarized camera(s) and the camera(s) that are not cross-polarized.

Abstract: The present invention sets forth a technique for generating two-dimensional (2D) renderings of a three-dimensional (3D) scene from an arbitrary camera position under arbitrary lighting conditions. This technique includes determining, based on a plurality of 2D representations of a 3D scene, a radiance field function for a neural radiance field (NeRF) model. This technique further includes determining, based on a plurality of 2D representations of a 3D scene, a radiance field function for a “one light at a time” (OLAT) model. The technique further includes rendering a 2D representation of the scene based on a given camera position and illumination data. The technique further includes computing a rendering loss based on the difference between the rendered 2D representation and an associated one of the plurality of 2D representations of the scene. The technique further includes modifying at least one of the NeRF and OLAT models based on the rendering loss.

Abstract: One or more embodiments comprise a computer-implemented method that includes receiving an input image including one or more facial representations and a set of points on a 3D canonical shape, wherein the set of points are selectable at runtime, extracting a set of features from the input image that represent at least one facial representation included in the one or more facial representations, and determining a set of landmarks on the at least one facial representation based on the set of features and the set of points, wherein each landmark in the set of landmarks is associated with at least one point in the set of points.

Abstract: A network interface device comprises a streaming data processing path comprising a first data processing engine and hubs. A first scheduler associated with a first hub controls an output of data by the first hub to the first data processing engine and a second scheduler associated with a second hub controls an output of data by the second hub. The first hub is arranged upstream of the first data processing engine on the data processing path and is configured to receive data from a first upstream data path entity and from a first data processing entity implemented in programmable circuitry via a data ingress interface of the first hub. The first data processing engine is configured to receive data from the first hub, process the received data and output the processed data to the second hub arranged downstream of first data processing engine.