Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

Abstract: Disclosed are systems and methods relating to extracting 3D features, such as bounding boxes. The systems can apply, to one or more features of a source image that depicts a scene using a first set of camera parameters, based on a condition view image associated with the source image, an epipolar geometric warping to determine a second set of camera parameters. The systems can generate, using a neural network, a synthetic image representing the one or more features and corresponding to the second set of camera parameters.

Abstract: A pellicle comprising a pellicle membrane with improved stability to hydrogen plasma is provided. The pellicle membrane includes a network of a plurality of carbon nanotubes. At least one carbon nanotube of the plurality of carbon nanotubes is surrounded by a multilayer protective coating that includes a stress control layer and a hydrogen permeation barrier layer over the stress control layer. The stress control layer and the hydrogen permeation barrier layer independently include an Me-containing nitride or an Me-containing oxynitride with Me selected from the group consisting of Si, Ti, Y, Hf, Zr, Zn, Mo, Cr and combinations thereof. The Me-containing nitride or the Me-containing oxynitride in the stress control layer has a first Me concentration, and the Me-containing nitride or the Me-containing oxynitride in the hydrogen permeation barrier layer has a second Me concentration less than the first Me concentration.

Abstract: In various examples, systems and methods are disclosed relating to neural networks for three-dimensional (3D) scene representations and modifying the 3D scene representations. In some implementations, a diffusion model can be configured to modify selected portions of 3D scenes represented using neural radiance fields, without painting back in content of the selected portions that was originally present. A first view of the neural radiance fields can be inpainted to remove a target feature from the first view, and used as guidance for updating the neural radiance field so that the target feature can be realistically removed from various second views of the neural radiance fields while context is retained outside of the selected portions.

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

Abstract: A mask characterization method comprises measuring an interference signal of a reflection or transmission mask for use in lithography; and determining a quality metric for the reflection or transmission mask based on the interference signal. A mask characterization apparatus comprises a light source arranged to illuminate a reflective or transmissive mask with light whereby mask-reflected or mask-transmitted light is generated; an optical grating arranged to convert the mask-reflected or mask-transmitted light into an interference pattern; and an optical detector array arranged to generate an interference signal by measuring the interference pattern.

Abstract: A reticle is provided. The reticle includes a first reflective multilayer (ML) over a mask substrate and a capping layer over the first reflective ML. The reticle also includes a first absorption layer over the capping layer and a second reflective multilayer (ML) over the first absorption layer. The reticle further includes an etch stop layer over the second reflective ML and a third reflective multilayer (ML) over the etch stop layer. In addition, the reticle includes an absorption film pair over the third reflective ML.

Abstract: A method for forming a pellicle for an extreme ultraviolet lithography is provided. The method includes forming a pellicle membrane over a filter membrane and transfer the pellicle membrane from the filter membrane to a membrane border. Forming the pellicle membrane includes growing carbon nanotubes (CNTs) from in-situ formed metal catalyst particles in a first reaction zone of a reactor, each of the CNTs including a metal catalyst particle at a growing tip thereof, promoting formation of bundles of nanotubes from the individual CNTs in a second zone of the reactor downstream of the first reaction zone. The bundled CNTs are then collected on the filter membrane.

Abstract: A pellicle for an EUV photo mask includes a membrane attached to a frame. The membrane includes nanotubes, Ru—O—X catalyst structures partially covering a surface of each nanotube, and a protection layer to cover the Ru—O—X catalyst structures and the surface of each nanotube. X is a metal element of Mo, Ti, Zr or Nb. The Ru—O—X catalyst structures include first nano-particles of a X-containing material formed on the surface of each nanotube, and second nano-particles of a Ru-containing material formed on the first nano-particles, thereby forming catalysts or catalyst bridges. The pellicle advantageously has high EUV light transmittance and improved endurance against attacking particles (such as hydrogen particles), thereby having prolonged lifetime.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be combined with a generative network to generate objects based on parameters associated with a textual input. An input including a 3D mesh and texture may be provided to a trained system along with a textual input that includes parameters for object generation. Features of the input object may be identified and then tuned in accordance with the textual input to generate a modified 3D object that includes a new texture along with one or more geometric adjustments.

Abstract: In various examples, systems and methods are disclosed relating to generating a response from image and/or video input for image/video-based artificial intelligence (AI) systems and applications. Systems and methods are disclosed for a first model (e.g., a teacher model) distilling its knowledge to a second model (a student model). The second model receives a downstream image in a downstream task and generates at least one feature. The first model generates first features corresponding to an image which can be a real image or a synthetic image. The second model generates second features using the image as an input to the second model. Loss with respect to first features is determined. The second model is updated using the loss.

Abstract: Systems and methods are provided for tracking sharing of an electronic content. An exemplary method may include receiving a request to access content associated with a web address by a user. Based on a unique identity assigned to the user and the web address, a unique tracking web address may be generated. This tracking web address may be shared with additional users. As other users request content associated with the tracking web address, information regarding the sharing of the electronic content may be determined and stored, allowing for tracking of sharing behavior of users.

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

Abstract: A mask for use in a semiconductor lithography process includes a substrate, a mask pattern disposed on the substrate, and a light absorbing border surrounding the mask pattern. The light absorbing border is inset from at least two edges of the substrate to define a peripheral region outside of the light absorbing border. In some designs, a first peripheral region extends from an outer perimeter of the light absorbing border to a first edge of the substrate, and a second peripheral region that extends from the outer perimeter of the light absorbing border to a second edge of the substrate, where the first edge of the substrate and the second edge of the substrate are on opposite sides of the mask pattern.

Abstract: A pellicle for an extreme ultraviolet (EUV) photomask includes a pellicle frame and a main membrane attached to the pellicle frame. The main membrane includes a plurality of nanotubes, and each of the plurality of nanotubes is covered by a coating layer containing Si and one or more metal elements.

Abstract: Apparatuses, systems, and techniques to annotate images using neural models. In at least one embodiment, neural networks generate mask information from labels of one or more objects within one or more images identified by one or more other neural networks.

Abstract: A method includes performing a lithography process using a mask and a pellicle membrane; detaching the pellicle membrane from the mask after the lithography process is completed; performing an inspection process to the pellicle membrane, the inspection process including generating a laser beam toward the pellicle membrane from a laser source, such that the laser beam passes through the pellicle membrane; and generating an image by receiving the laser beam passing through the pellicle membrane using an image sensor; and determining whether a particle is present on the pellicle membrane or a pin hole is present in the pellicle membrane based on the image.

Abstract: A mask for use in a semiconductor lithography process includes a substrate, a mask pattern disposed on the substrate, and a light absorbing border surrounding the mask pattern. The light absorbing border is inset from at least two edges of the substrate to define a peripheral region outside of the light absorbing border. In some designs, a first peripheral region extends from an outer perimeter of the light absorbing border to a first edge of the substrate, and a second peripheral region that extends from the outer perimeter of the light absorbing border to a second edge of the substrate, where the first edge of the substrate and the second edge of the substrate are on opposite sides of the mask pattern.

Abstract: A pellicle assembly includes a pellicle membrane with a nanotube layer formed from thick nanotube bundles. The pellicle membrane can be formed with multiple layers and has a combination of long lifetime, high transmittance, low deflection, and small pore size. A conformal coating may applied to an outer surface of the pellicle membrane. The conformal coating protects the pellicle membrane from damage that can occur due to heat and hydrogen plasma created during EUV exposure.