-
公开(公告)号:US20250095258A1
公开(公告)日:2025-03-20
申请号:US18370607
申请日:2023-09-20
Applicant: Google LLC
Inventor: Crystal Fong , Nicholas Wasilewski , Douglas Sim Dietrich, JR.
Abstract: A method includes identifying a first three-dimensional (3D) object comprising a first animation rig covering a first set of features associated with the first 3D object. An indication of the first 3D object is provided as input to a machine-learning model. The machine-learning model is trained to generate, using a second 3D object comprising a second animation rig, an animation sequence for the first 3D object. The second animation rig covers a second set of features associated with the second 3D object and the second set of features comprises the first set of features and one or more additional features. One or more outputs of the machine-learning model is obtained. The one or more obtained outputs comprise a plurality of animation frames reflecting an animation sequence for the first 3D object.
-
公开(公告)号:US20230140250A1
公开(公告)日:2023-05-04
申请号:US17767909
申请日:2019-10-10
Applicant: GOOGLE LLC
Inventor: Douglas Sim Dietrich, JR. , Robert McCool , Jean-François Roy , Michael S. Green , Gurudas Somadder
IPC: H04N21/2343 , H04N21/234 , H04N21/81
Abstract: A system includes a video source device connected to a video destination device via a network. The video source device includes a network interface and an encoder coupled to the network interface. The encoder is configured to encode a first stream of rendered video frames having a first frame rate to generate a second stream of encoded video frames for transmission over the network via the network interface, wherein the second stream has a second frame rate greater than the first frame rate. As part of this encoding process, the encoder is configured to selectively encode multiple instances of at least one video frame of the first stream for inclusion in the second stream to compensate for the difference between the first frame rate and the second frame rate.
-
公开(公告)号:US20250104330A1
公开(公告)日:2025-03-27
申请号:US18725519
申请日:2022-01-05
Applicant: GOOGLE LLC
Inventor: Douglas Sim Dietrich, JR.
Abstract: Systems and techniques are provided for dynamically modifying an intersection acceleration structure (IAS) used to accelerate ray cast rendering of a three-dimensional (3D) scene. A frame of the 3D scene is rendered via a set of ray casting operations performed in accordance with a first IAS, the first IAS including a plurality of bounding volumes that each includes a portion of the 3D scene. For each bounding volume, a subset of virtual light rays is tracked, the virtual light rays being associated with the set of ray casting operations and encountering the bounding volume during the rendering of the frame. Based on the subset of virtual light rays associated with each bounding volume, a modified second IAS is generated for rendering the 3D scene.
-
-