-
公开(公告)号：US20240273871A1
公开(公告)日：2024-08-15
申请号：US18168867
申请日：2023-02-14
Applicant: Lemon Inc.
Inventor： Guoxian Song , Hongyi Xu , Jing Liu , Tiancheng Zhi , Yichun Shi , Jianfeng Zhang , Zihang Jiang , Jiashi Feng , Shen Sang , Linjie Luo
CPC classification number: G06V10/7715 , G06V10/28 , G06V10/454
Abstract: A method for generating a multi-dimensional stylized image. The method includes providing input data into a latent space for a style conditioned multi-dimensional generator of a multi-dimensional generative model and generating the multi-dimensional stylized image from the input data by the style conditioned multi-dimensional generator. The method further includes synthesizing content for the multi-dimensional stylized image using a latent code and corresponding camera pose from the latent space to formulate an intermediate code to modulate synthesis convolution layers to generate feature images as multi-planar representations and synthesizing stylized feature images of the feature images for generating the multi-dimensional stylized image of the input data. The style conditioned multi-dimensional generator is tuned using a guided transfer learning process using a style prior generator.
-
公开(公告)号：US20240135621A1
公开(公告)日：2024-04-25
申请号：US18046073
申请日：2022-10-12
Applicant: Lemon Inc. , Beijing Zitiao Network Technology Co., Ltd.
Inventor： Shen SANG , Tiancheng Zhi , Guoxian Song , Jing Liu , Linjie Luo , Chunpong Lai , Weihong Zeng , Jingna Sun , Xu Wang
CPC classification number: G06T15/00 , G06T7/62 , G06V10/56 , G06V10/751 , G06V10/761 , G06T2207/10024 , G06T2207/30201
Abstract: A method of generating a stylized 3D avatar is provided. The method includes receiving an input image of a user, generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image, and providing the stylized image to a first model to generate a first plurality of parameters. The first plurality of parameters include a discrete parameter and a continuous parameter. The method further includes providing the stylized image and the first plurality of parameters to a second model that is trained to generate an avatar image, receiving, from the second model, the avatar image, comparing the stylized image to the avatar image, based on a loss function, to determine an error, updating the first model to generate a second plurality of parameters that correspond to the first plurality of parameters, based on the error, and providing the second plurality of parameters as an output.
-
公开(公告)号：US20250157109A1
公开(公告)日：2025-05-15
申请号：US18388785
申请日：2023-11-10
Applicant: Lemon Inc.
Inventor： Peilin Li , Guoxian Song
Abstract: The present disclosure describes techniques for creating a real-time interactive video. A source image is generated by a first machine learning model based on capturing an image of a user. The image comprises a face of the user. One or more facial images of the user are captured. The one or more facial images depict one or more facial expressions. The source image and information extracted from the one or more facial images are input into a second machine learning model. The second machine learning model is configured and trained to transfer facial expressions of creators to machine-generated images in real-time. The real-time interactive video is created by dynamically driving the source image based on the one or more facial expressions.
-
公开(公告)号：US12148095B2
公开(公告)日：2024-11-19
申请号：US17932640
申请日：2022-09-15
Applicant: Lemon Inc.
Inventor： Tiancheng Zhi , Shen Sang , Guoxian Song , Chunpong Lai , Jing Liu , Linjie Luo
Abstract: Systems and methods for rendering a translucent object are provided. In one aspect, the system includes a processor coupled to a storage medium that stores instructions, which, upon execution by the processor, cause the processor to receive at least one mesh representing at least one translucent object. For each pixel to be rendered, the processor performs a rasterization-based differentiable rendering of the pixel to be rendered using the at least one mesh and determines a plurality of values for the pixel to be rendered based on the rasterization-based differentiable rendering. The rasterization-based differentiable rendering can include performing a probabilistic rasterization process along with aggregation techniques to compute the plurality of values for the pixel to be rendered. The plurality of values includes a set of color channel values and an opacity channel value. Once values are determined for all pixels, an image can be rendered.
-
公开(公告)号：US20230410267A1
公开(公告)日：2023-12-21
申请号：US17807527
申请日：2022-06-17
Applicant: Lemon Inc. , Beijing Zitiao Network Technology Co., Ltd.
Inventor： Guoxian Song , Jing Liu , Weihong Zeng , Jingna Sun , Xu Wang , Linjie Luo
CPC classification number: G06T5/50 , G06T3/4046 , G06V40/168 , G06T2207/20084 , G06T2207/20132 , G06T2207/20081 , G06T2207/20221 , G06T2207/30201
Abstract: Methods and systems for enlarging a stylized region of an image are disclosed that include receiving an input image, generating, using a first generative adversarial network (GAN) generator, a first stylized image, based on the input image, normalizing the input image, generating, using a second generative adversarial network (GAN) generator, a second stylized image, based on the normalized input image, blending the first stylized image and the second stylized image to obtain a third stylized image, and providing the third stylized image as an output.
-
Patent Agency Ranking
公开(公告)号：US12217466B2
公开(公告)日：2025-02-04
申请号：US17519711
申请日：2021-11-05
Applicant: Lemon Inc.
Inventor： Jing Liu , Chunpong Lai , Guoxian Song , Linjie Luo
Abstract: Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.
-
公开(公告)号：US20240265621A1
公开(公告)日：2024-08-08
申请号：US18165794
申请日：2023-02-07
Applicant: Lemon Inc.
Inventor： Hongyi Xu , Guoxian Song , Zihang Jiang , Jianfeng Zhang , Yichun Shi , Jing Liu , Wanchun Ma , Jiashi Feng , Linjie Luo
CPC classification number: G06T15/08 , G06T3/4046 , G06T3/4053 , G06V40/176
Abstract: Technologies are described and recited herein for producing controllable synthesized images include a geometry guided 3D GAN framework for high-quality 3D head synthesis with full control on camera poses, facial expressions, head shape, articulated neck and jaw poses; and a semantic SDF (signed distance function) formulation that defines volumetric correspondence from observation space to canonical space, allowing full disentanglement of control parameters in 3D GAN training.
-
公开(公告)号：US11720994B2
公开(公告)日：2023-08-08
申请号：US17321384
申请日：2021-05-14
Applicant: Lemon Inc.
Inventor： Linjie Luo , Guoxian Song , Jing Liu , Wanchun Ma
CPC classification number: G06T3/0012 , G06F18/214 , G06N3/045 , G06N3/08 , G06T3/0006 , G06T5/00 , G06T11/00 , G06T2207/20016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30201
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：US20230124252A1
公开(公告)日：2023-04-20
申请号：US17501990
申请日：2021-10-14
Applicant: Lemon Inc.
Inventor： Jing Liu , Chunpong Lai , Guoxian Song , Linjie Luo , Ye Yuan
Abstract: Systems and method directed to generating a stylized image are disclosed. In particular, the method includes, in a first data path, (a) applying first stylization to an input image and (b) applying enlargement to the stylized image from (a). The method also includes, in a second data path, (c) applying segmentation to the input image to identify a face region of the input image and generate a mask image, and (d) applying second stylization to an entirety of the input image and inpainting to the identified face region of the stylized image. Machine-assisted blending is performed based on (1) the stylized image after the enlargement from the first data path, (2) the inpainted image from the second data path, and (3) the mask image, in order to obtain a final stylized image.
-
公开(公告)号：US12260485B2
公开(公告)日：2025-03-25
申请号：US18046077
申请日：2022-10-12
Applicant: Lemon Inc.
Inventor： Guoxian Song , Shen Sang , Tiancheng Zhi , Jing Liu , Linjie Luo
Abstract: A method of generating a style image is described. The method includes receiving an input image of a subject. The method further includes encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code. The method further includes decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image.
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.014 seconds)
