公开(公告)号：WO2022240354A1

公开(公告)日：2022-11-17

申请号：PCT/SG2022/050221

申请日：2022-04-14

Applicant: LEMON INC.

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

IPC: G06N3/04 ,  G06N3/08 ,  G06V10/77 ,  G06K9/62 ,  G06F18/214 ,  G06N3/045 ,  G06N3/047 ,  G06N3/088 ,  G06T11/00 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201 ,  G06T3/0006 ,  G06T3/0012 ,  G06T5/00

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.

公开(公告)号：WO2023009060A1

公开(公告)日：2023-02-02

申请号：PCT/SG2022/050345

申请日：2022-05-24

Applicant: LEMON INC.

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

IPC: G06V10/82 ,  G06V40/16 ,  G06N3/0464

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：WO2023018369A2

公开(公告)日：2023-02-16

申请号：PCT/SG2022/050531

申请日：2022-07-26

Applicant: LEMON INC.

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

IPC: G06V40/16 ,  G06V10/82 ,  G06N3/09 ,  G06T7/246 ,  G06F18/2193 ,  G06T13/40 ,  G06T13/80 ,  G06T2207/20084 ,  G06T2207/30201 ,  G06T7/251 ,  G06V10/242 ,  G06V40/171 ,  G06V40/176

Abstract: The present disclosure describes techniques for facial expression recognition. A first loss function may be determined based on a first set of feature vectors associated with a first set of images depicting facial expressions and a first set of labels indicative of the facial expressions. A second loss function may be determined based on a second set of feature vectors associated with a second set of images depicting asymmetric facial expressions and a second set of labels indicative of the asymmetric facial expressions. The first loss function and the second loss function may be used to determine a maximum loss function. The maximum loss function may be applied during training of a model. The trained model may be configured to predict at least one asymmetric facial expression in a subsequently received image.

公开(公告)号：EP4268136A1

公开(公告)日：2023-11-01

申请号：EP22807950.5

申请日：2022-04-14

Applicant: Lemon Inc.

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

IPC: G06N3/04 ,  G06N3/08 ,  G06V10/77 ,  G06K9/62