Autodesk, Inc.

Google Inc.

Highlightcam, Inc.

Martin Wicke

Saul Thomas Griffith

Jonathan Bachrach

Tucker Gilman

Geoffrey Irving

Keith Pasko

Daniel Benoit

Anelia Angelova

Reza Mahjourian

Samuel Eli Calisch

Sam Calisch

Michael James O'Kelly

Michael Katsevman

Robert Neivert

A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

Unsupervised learning of image depth and ego-motion prediction neural networks

A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

Image depth prediction neural networks

Embodiments disclosed herein provide systems and methods for preparing geometry for 3D printing. In one embodiment, a 3D printing preparation application receives 3D geometry and repairs non-manifold edges and non-manifold vertices, producing a topological manifold geometry. The 3D printing preparation application then welds coincident edges without coincident faces and fills holes in the geometry. The 3D printing preparation application may further perform resolution-aware thickening of the geometry by estimating distances to a medial axis based on distances to distance field shocks, and advecting the distance field using a velocity field. A similar approach may be used to perform resolution-aware separation enforcement. Alternatively, one component may be globally thickened and subtracted from another for separation enforcement. The 3D printing preparation application may also split large models and add connectors for connecting the split pieces after printing. In addition, the 3D printing preparation application may generate a 3D print preview.

Three-dimensional printing preparation

Embodiments of the invention provide systems and methods for nesting objects in 2D sheets and 3D volumes. In one embodiment, a nesting application simplifies the shapes of parts and performs a rigid body simulation of the parts dropping into a 2D sheet or 3D volume. In the rigid body simulation, parts begin from random initial positions on one or more sides and drop under the force of gravity into the 2D sheet or 3D volume until coming into contact with another part, a boundary, or the origin of the gravity. The parts may be dropped according to a particular order, such as alternating large and small parts. Further, the simulation may be translation- and/or position-only, meaning the parts do not rotate and/or do not have momentum, respectively. Tighter packing may be achieved by incorporating user inputs and simulating jittering of the parts using random forces.

Nesting using rigid body simulation

Embodiments disclosed herein provide techniques for decomposing 3D geometry into developable surface patches and cut patterns. In one embodiment, a decomposition application receives a triangulated 3D surface as input and determines approximately developable surface patches from the 3D surface using a variant of k-means clustering. Such approximately developable surface patches may have undesirable jagged boundaries, which the decomposition application may eliminate by generating a data structure separate from the mesh that contains patch boundaries and optimizing the patch boundaries or, alternatively, remeshing the mesh such that patch boundaries fall on mesh edges. The decomposition application may then flatten the patches into truly developable surfaces by re-triangulating the patches as ruled surfaces. The decomposition application may further flatten the ruled surfaces into 2D shapes and lay those shapes out on virtual sheets of material. A person, or machinery, may cut out those shapes from physical sheets of material based on the layout.

Decomposition of 3D geometry into developable surface patches and 2D cut patterns

A method for editing content, including receiving content from content storage, calculating a score for each frame of the content based on weighted parameter scores, grouping frames into frame groups, calculating a group score for each frame group based on the scores of the frames within the frame group; selecting frame groups having a group score beyond a score threshold, comparing a total length of the selected frame groups to a target length with the system, adjusting the score threshold until the total length of the selected frame groups substantially matches the target length with the system, combining the selected frame groups into a video with the system, and sending the video to a device with the system.

Growing community of inventors

San Francisco, CA, United States of America

Martin Wicke