Abstract: In some embodiments, a method receives a video including interlaced frames. Second fields for a second frame and the second fields for a third frame are analyzed to determine estimated second fields for the first frame in an image space. The method converts the first fields and the estimated second fields for the first frame into first features and second features, respectively, in a feature space. The estimated second features are determined for the estimated second fields for the first frame based on the first features for the first frame. Backward features from the second frame and forward features from the third frame are used to determine the estimated second features for the first frame. The method outputs a prediction for the estimated second fields for the first frame based on the estimated second features and generates a first frame with the first fields and estimated second fields.

Abstract: In some embodiments, a grain analysis system is configured for analyzing a first video frame and outputting respective first film grain information for film grain that is included in the first video frame or configured for analyzing a second video frame and outputting second film grain information. At least one of a grain removal system and a grain synthesis system is included. The grain removal system is configured for removing the film grain from the first video frame using the first film grain information to generate a third video frame corresponding to the first video frame with film grain removed. The grain analysis system is separate from the grain removal system. The grain synthesis system is configured for synthesizing film grain for the third video frame using the first film grain information or the second film grain information. The grain analysis system is separate from the grain synthesis system.

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: Embodiment of the present invention sets forth techniques for performing face reconstruction. The techniques include generating an identity mesh based on an identity encoding that represents an identity associated with a face in one or more images. The techniques also include generating an expression mesh based on an expression encoding that represents an expression associated with the face in the one or more images. The techniques also include generating, by a machine learning model, an output mesh of the face based on the identity mesh and the expression mesh.

Abstract: Techniques are disclosed for generating photorealistic images of objects, such as heads, from multiple viewpoints. In some embodiments, a morphable radiance field (MoRF) model that generates images of heads includes an identity model that maps an identifier (ID) code associated with a head into two codes: a deformation ID code encoding a geometric deformation from a canonical head geometry, and a canonical ID code encoding a canonical appearance within a shape-normalized space. The MoRF model also includes a deformation field model that maps a world space position to a shape-normalized space position based on the deformation ID code. Further, the MoRF model includes a canonical neural radiance field (NeRF) model that includes a density multi-layer perceptron (MLP) branch, a diffuse MLP branch, and a specular MLP branch that output densities, diffuse colors, and specular colors, respectively. The MoRF model can be used to render images of heads from various viewpoints.

Abstract: A composition including a temperature sensitive biocompatible solder and at least one type of nanoparticles, characterized in that a first type of nanoparticles is a fluorescent nanothermometer, wherein the fluorescent nanothermometer exhibits an excitation maximum and temperature dependent emission spectrum each in the range of between 650 and 1350 nm. The composition can be used for laser tissue soldering.

Abstract: One embodiment of the present invention sets forth a technique for generating actuation values based on a target shape such that the actuation values cause a simulator to output a simulated soft body that matches the target shape. The technique includes inputting a latent code that represents a target shape and a point on a geometric mesh into a first machine learning model. The technique further includes generating, via execution of the first machine learning model, one or more simulator control values that specify a deformation of the geometric mesh, where each of the simulator control values is based on the latent code and corresponds to the input point, and generating, via execution of the simulator, a simulated soft body based on the one or more simulator control values and the geometric mesh. The technique further includes causing the simulated soft body to be outputted to a computing device.

Abstract: The present invention provides additive manufacturing compositions, also referred as “inks” in the field of additive manufacturing, which can be fine-tuned with respect to porosity by varying the intensity of the photopolymerisation light source and which can further be used to obtain objects out of glasses, ceramics or glass-ceramics and their respective alloys.

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: 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: In some embodiments, a method trains a first parameter of a differentiable proxy codec to encode source content based on a first loss between first compressed source content and second compressed source content that is output by a target codec. A pre-processor pre-processes a source image to output a pre-processed source image, the pre-processing being based on a second parameter. The differentiable proxy codec encodes the pre-processed source image into a compressed pre-processed source image based on the first parameter. The method determines a second loss between the source image and the compressed pre-processed source image and determines an adjustment to the first parameter based on the second loss. The adjustment is used to adjust the second parameter of the pre-processor based on the second loss.

Abstract: A system includes a computing platform having a hardware processor and a memory storing a software code and a neural network (NN) having multiple layers including a last activation layer and a loss layer. The hardware processor executes the software code to identify different combinations of layers for testing the NN, each combination including candidate function(s) for the last activation layer and candidate function(s) for the loss layer. For each different combination, the software code configures the NN based on the combination, inputs, into the configured NN, a training dataset including multiple data objects, receives, from the configured NN, a classification of the data objects, and generates a performance assessment for the combination based on the classification. The software code determines a preferred combination of layers for the NN including selected candidate functions for the last activation layer and the loss layer, based on a comparison of the performance assessments.

Abstract: Techniques are disclosed for training and applying a denoising model. The denoising model includes multiple specialized denoisers and a generalizer, each of which is a machine learning model. The specialized denoisers are trained to denoise images associated with specific ranges of noise parameters. The generalizer is trained to generate per-pixel denoising kernels for denoising images associated with arbitrary noise parameters using outputs of the specialized denoisers. Subsequent to training, a noisy image, such as a live-action image or a rendered image, can be denoised by inputting the noisy image into the specialized denoisers to obtain intermediate denoised images that are then input, along with the noisy image, into the generalizer to obtain per-pixel denoising kernels, which can be normalized and applied to denoise the noisy image.

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: A system processing hardware executes a machine learning (ML) model-based video compression encoder to receive uncompressed video content and corresponding motion compensated video content, compare the uncompressed and motion compensated video content to identify an image space residual, transform the image space residual to a latent space representation of the uncompressed video content, and transform, using a trained image compression ML model, the motion compensated video content to a latent space representation of the motion compensated video content.

Abstract: In some embodiments, a system includes a first component to extract temporal features from a current frame being coded and a previous frame of a video. A second component uses a first transformer to fuse spatial features from the current frame with the temporal features to generate spatio-temporal features as first output. A third component uses a second transformer to perform entropy coding using the first output and at least a portion of the temporal features to generate a second output. A fourth component uses a third transformer to reconstruct the current frame based on the first output that is processed using the second output and the temporal features.

Abstract: The present invention relates to energy storage systems and reactors useful in such systems. Inventive reactors comprise a reaction vessel defining an inner volume and a compensation element, whereby said inner volume is filled with a fixed bed that is free of cavities and that comprises particles of formula (I), FeOx (I), where 0?x?1.5; said compensation element is adapted to adjust said inner volume. The reactors are inherently explosion proof and thus suited for domestic use. The systems are useful for compensating long-term fluctuations observed in production of renewable energy.

Abstract: The present disclosure relates to a method for producing calcium carbonate solids from alkaline minerals including the following method steps: Supplying alkaline minerals and an extraction agent into a reactor tank. Stirring the alkaline minerals and the extraction agent in the reactor tank such that a first suspension is formed. Draining of the first suspension from the reactor tank and separating a liquid phase comprising calcium from the first suspension and transferring the liquid phase into a carbonation tank. Supplying a gas comprising CO2 into the carbonation tank, wherein the consumption of CO2 results in the precipitation of calcium carbonate solids thereby generating a second suspension and nucleating and growing of the calcium carbonate solids. Furthermore, a measure of the consumed CO2 is determined by at least one sensor.

Abstract: The invention relates to a compound of formula (I) wherein A1, A2, X and R1-R3 are as defined in the description and in the claims. The compound of formula (I) can be used as a medicament.

Abstract: The present invention relates to a time-continuous neural network circuit implemented on analog hardware with device mismatch, the circuit including a control unit (40) which is individually connected to each respective neuron of the circuit, the neurons in the hidden and output layers comprising a forward compartment for processing signals coming from preceding layers, a feedback compartment for processing feedback signals coming from the control unit and a central compartment for generating and sending a signal to the next layer or to the control unit. The control unit generates and sends to the feedback compartment of each respective neuron a feedback signal (Sf) based on the comparison between a network output signal (Sout) and a target signal (Star).