公开(公告)号：US20230377368A1

公开(公告)日：2023-11-23

申请号：US17751393

申请日：2022-05-23

Applicant: LEMON Inc.

Inventor： Shuo CHENG ,  Guoxian SONG ,  Wanchun MA ,  Chao Wang ,  Linjie LUO

IPC: G06V40/16 ,  G06V10/74 ,  G06V10/82 ,  G06T11/60

CPC classification number: G06V40/172 ,  G06V10/761 ,  G06V10/82 ,  G06T11/60

Abstract: Methods and systems for generating synthetic images based on an input image are described. The method may include receiving an input image; generating, using an encoder, a first latent code vector representation based on the input image; receiving a latent code corresponding to a feature to be added to the input image; modifying the first latent code vector representation based on the latent code corresponding to the feature to be added; generating, by an image decoder, a synthesized image based on the modified first latent code vector representation; identifying, using a landmark detector, one or more landmarks in the base image; identifying, using a landmark detector, one or more landmarks in the synthesized image; determining a measure of similarity between the landmark identified on the base image and the landmark identified in the synthesized image; and discarding the synthesized image based on the comparison.

公开(公告)号：US20230036903A1

公开(公告)日：2023-02-02

申请号：US17390440

申请日：2021-07-30

Applicant: Lemon Inc.

Inventor： Wanchun MA ,  Shuo CHENG ,  Chao WANG ,  Michael Leong Hou TAY ,  Linjie LUO

IPC: G06T13/40 ,  G06K9/00 ,  G06N3/08

Abstract: The present disclosure describes techniques for face tracking. The techniques comprise receiving landmark data associated with a plurality of images indicative of at least one facial part. Representative images corresponding to the plurality of images may be generated based on the landmark data. Each representative image may depict a plurality of segments, and each segment may correspond to a region of the at least one facial part. The plurality of images and corresponding representative images may be input into a neural network to train the neural network to predict a feature associated with a subsequently received image comprising a face. An animation associated with a facial expression may be controlled based on output from the trained neural network.

公开(公告)号：US20220375024A1

公开(公告)日：2022-11-24

申请号：US17321384

申请日：2021-05-14

Applicant: Lemon Inc.

Inventor： Linjie LUO ,  Guoxian SONG ,  Jing LIU ,  Wanchun MA

IPC: G06T3/00 ,  G06T11/00 ,  G06T5/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and method directed to an inversion-consistent transfer learning framework for generating portrait stylization using only limited exemplars. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be provided to a generative adversarial network (GAN) generator to generate a stylized image. In examples, the variational autoencoder is trained using a plurality of images while keeping the weights of a pre-trained GAN generator fixed, where the pre-trained GAN generator acts as a decoder for the encoder. In other examples, a multi-path attribute aware generator is trained using a plurality of exemplar images and learning transfer using the pre-trained GAN generator.