公开(公告)号：US20240005587A1

公开(公告)日：2024-01-04

申请号：US17856362

申请日：2022-07-01

Applicant: ADOBE INC.

Inventor： Kuldeep KULKARNI ,  Aniruddha MAHAPATRA

IPC: G06T13/80 ,  G06T7/215 ,  G06T3/00

CPC classification number: G06T13/80 ,  G06T7/215 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/10016 ,  G06T3/0093

Abstract: Systems and methods for machine learning based controllable animation of still images is provided. In one embodiment, a still image including a fluid element is obtained. Using a flow refinement machine learning model, a refined dense optical flow is generated for the still image based on a selection mask that includes the fluid element and a dense optical flow generated from a motion hint that indicates a direction of animation. The refined dense optical flow indicates a pattern of apparent motion for the at least one fluid element. Thereafter, a plurality of video frames is generated by projecting a plurality of pixels of the still image using the refined dense optical flow.

公开(公告)号：US20240135197A1

公开(公告)日：2024-04-25

申请号：US17962962

申请日：2022-10-10

Applicant: Adobe Inc.

Inventor： Vishwa VINAY ,  Tirupati Saketh CHANDRA ,  Rishi AGARWAL ,  Kuldeep KULKARNI ,  Hiransh GUPTA ,  Aniruddha MAHAPATRA ,  Vaidehi Ramesh PATIL

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: Embodiments are disclosed for expanding a seed scene using proposals from a generative model of scene graphs. The method may include clustering subgraphs according to respective one or more maximal connected subgraphs of a scene graph. The scene graph includes a plurality of nodes and edges. The method also includes generating a scene sequence for the scene graph based on the clustered subgraphs. A first machine learning model determines a predicted node in response to receiving the scene sequence. A second machine learning model determines a predicted edge in response to receiving the scene sequence and the predicted node. A scene graph is output according to the predicted node and the predicted edge.