Seagate Technology Incorporated

Sandisk Corporation

Nanosys, Inc.

Nvidia Corporation

Honeywell International Inc.

Analog Devices,inc.

Chao Liu

J Wallace Parce

Xiangfeng Duan

Jian Chen

Karen Chu Cruden

Dieter Klaus Weller

Timothy John Klemmer

Srikanth Ranganathan

Madhuri Nallabolu

Xiaomin Yang

David Leslie Heald

Nisha Shukla

Jan Kautz

Joel Gamoras

Kihwan Kim

Anjul Patney

Jinwei Gu

Hong Min Huang

Earl Chrzaszcz Johns

Helen Xiao Xu

Anthonius Bakker

Iuri Frosio

Andrew Robert Eckert

Paul Bernatis

Christopher Bongsoo Choy

Hongxu Yin

Ben Eckart

Yurong You

Yazhou Xing

Amrita Mazumdar

Madhuri L Nallabolu

One or more embodiments include receiving one or more frames of a live video captured by a video capturing device, wherein the one or more frames include a current frame that is most-recently captured, identifying a set of reference frames included in the one or more frames based on at least the current frame, wherein each frame in the set of reference frames has a different exposure level relative to the current frame, determining, using one or more neural networks, a set of missing details for one or more regions of the current frame based on the set of reference frames, generating an updated version of the current frame based on the set of details, and outputting the updated version of the current frame in real-time.

Hallucinating details for over-exposed pixels in videos using learned reference frame selection

In various embodiments, an unsupervised training application executes a neural network on a first point cloud to generate keys and values. The unsupervised training application generates output vectors based on a first query set, the keys, and the values and then computes spatial features based on the output vectors. The unsupervised training application computes quantized context features based on the output vectors and a first set of codes representing a first set of 3D geometry blocks. The unsupervised training application modifies the first neural network based on a likelihood of reconstructing the first point cloud, the quantized context features, and the spatial features to generate an updated neural network. A trained machine learning model includes the updated neural network, a second query set, and a second set of codes representing a second set of 3D geometry blocks and maps a point cloud to a representation of 3D geometry instances.

Computer-based techniques for learning compositional representations of 3D point clouds

Techniques for estimating depth for a video stream captured by a monocular image sensor are disclosed. A sequence of image frames are captured by the monocular image sensor. A first neural network is configured to process at least a portion of the sequence of image frames to generate a depth probability volume. The depth probability volume includes a plurality of probability maps corresponding to a number of discrete depth candidate locations over a range of depths defined for the scene. The depth probability volume can be updated using a second neural network that is configured to generate adaptive gain parameters to integrate the DPVs over time. A third neural network is configured to refine the updated depth probability volume from a lower resolution to a higher resolution that matches the original resolution of the sequence of image frames. A depth map can be calculated based on the depth probability volume.

Estimating depth for a video stream captured with a monocular rgb camera

A composition for forming a coating is provided including at least one oxysilane-containing polymer or oligomer having an oxysilane group and at least one other organic crosslinkable group; an endcapping agent; and a solvent. A coated substrate, wherein the substrate is a silicon wafer or coated silicon wafer, includes an organic planarization layer in contact with the substrate, a photoresist layer, and a middle layer positioned between the organic planarization layer and the photoresist layer. The middle layer is formed from a composition including at least one oxysilane-containing polymer or oligomer having an oxysilane group and at least one other organic crosslinkable group, an endcapping agent; and a solvent.

Low temperature SC1 strippable oxysilane-containing coatings

Methods for forming or patterning nanostructure arrays are provided. The methods involve formation of arrays on coatings comprising nanostructure association groups, formation of arrays in spin-on-dielectrics, solvent annealing after nanostructure deposition, patterning using resist, and/or use of devices that facilitate array formation. Related devices for forming nanostructure arrays are also provided, as are devices including nanostructure arrays (e.g., memory devices). Methods for protecting nanostructures from fusion during high temperature processing also are provided.

Methods and devices for forming nanostructure monolayers and devices including such monolayers

Methods are provided for forming a nanostructure array. An example method includes providing a first layer, providing nanostructures dispersed in a solution comprising a liquid form of a spin-on-dielectric, wherein the nanostructures comprise a silsesquioxane ligand coating, disposing the solution on the first layer, whereby the nanostructures form a monolayer array on the first layer, and curing the liquid form of the spin-on-dielectric to provide a solid form of the spin-on-dielectric. Numerous other aspects are provided.

Methods for forming or patterning nanostructure arrays are provided. The methods involve formation of arrays on coatings comprising nanostructure association groups, formation of arrays in spin-on-dielectrics, solvent annealing after nanostructure deposition, patterning using resist, and/or use of devices that facilitate array formation. Related devices for forming nanostructure arrays are also provided, as are devices including nanostructure arrays (e.g., memory devices).

Methods for forming or patterning nanostructure arrays are provided. The methods involve formation of arrays on coatings comprising nanostructure association groups, formation of arrays in spin-on-dielectrics, solvent annealing after nanostructure deposition, patterning using resist, and/or use of devices that facilitate array formation. Related devices for forming nanostructure arrays are also provided, as are devices including nanostructure arrays (e.g., memory devices). Methods for protecting nanostructures from fusion during high temperature processing are also provided.

An apparatus includes a substrate, a magnetically soft underlayer on the substrate, and a plurality of generally cubic FePt nanoparticles on the magnetically soft underlayer, wherein the nanoparticles have a magnetization in a direction substantially normal to a surface of the magnetically soft underlayer. The FePt nanoparticles can have magnetically easy axes perpendicular to the surface of the soft underlayer.

Method of producing self-assembled cubic FePt nanoparticles and apparatus using same

Methods for forming or patterning nanostructure arrays are provided. The methods involve formation of arrays on coatings comprising nanostructure association groups, patterning using resist, and/or use of devices that facilitate array formation. Related devices for forming nanostructure arrays are also provided, as are devices including nanostructure arrays (e.g., memory devices).

Methods for producing electronic grade metal nanostructures having low levels of contaminants are provided. Monolayer arrays, populations, and devices including such electronic grade nanostructures are described. In addition, novel methods and compositions for production of Group 10 metal nanostructures and for production of ruthenium nanostructures are provided, along with methods for recovering nanostructures from suspension.

Electronic grade metal nanostructures

A method comprises: heating a solution of platinum acetylacetonate, Fe(CO), oleic acid, and oleylamine in dichlorobenzene to a reflux temperature, refluxing the solution, and using the solution to deposit FePt nanoparticles. A magnetic storage medium that includes cubic FePt particles is also provided.

Growing community of inventors

San Jose, CA, United States of America

Chao Liu