JP7373554B2 - クロスドメイン画像変換 - Google Patents
クロスドメイン画像変換 Download PDFInfo
- Publication number
- JP7373554B2 JP7373554B2 JP2021512501A JP2021512501A JP7373554B2 JP 7373554 B2 JP7373554 B2 JP 7373554B2 JP 2021512501 A JP2021512501 A JP 2021512501A JP 2021512501 A JP2021512501 A JP 2021512501A JP 7373554 B2 JP7373554 B2 JP 7373554B2
- Authority
- JP
- Japan
- Prior art keywords
- image
- geometry
- style
- domain
- transformation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/18—Image warping, e.g. rearranging pixels individually
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—Two-dimensional [2D] image generation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811294026.6 | 2018-10-31 | ||
| CN201811294026.6A CN111127304B (zh) | 2018-10-31 | 2018-10-31 | 跨域图像转换 |
| PCT/US2019/049619 WO2020091891A1 (en) | 2018-10-31 | 2019-09-05 | Cross-domain image translation |
Publications (4)
| Publication Number | Publication Date |
|---|---|
| JP2022503647A JP2022503647A (ja) | 2022-01-12 |
| JP2022503647A5 JP2022503647A5 (https=) | 2022-08-18 |
| JPWO2020091891A5 JPWO2020091891A5 (https=) | 2022-08-18 |
| JP7373554B2 true JP7373554B2 (ja) | 2023-11-02 |
Family
ID=67957460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2021512501A Active JP7373554B2 (ja) | 2018-10-31 | 2019-09-05 | クロスドメイン画像変換 |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US11481869B2 (https=) |
| EP (1) | EP3874458A1 (https=) |
| JP (1) | JP7373554B2 (https=) |
| KR (1) | KR102663519B1 (https=) |
| CN (1) | CN111127304B (https=) |
| WO (1) | WO2020091891A1 (https=) |
Families Citing this family (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127304B (zh) * | 2018-10-31 | 2024-02-20 | 微软技术许可有限责任公司 | 跨域图像转换 |
| US20200242736A1 (en) * | 2019-01-29 | 2020-07-30 | Nvidia Corporation | Method for few-shot unsupervised image-to-image translation |
| US11556848B2 (en) * | 2019-10-21 | 2023-01-17 | International Business Machines Corporation | Resolving conflicts between experts' intuition and data-driven artificial intelligence models |
| US12050639B2 (en) * | 2019-11-12 | 2024-07-30 | Yahoo Assets Llc | Method and system for sketch based search |
| US11450008B1 (en) * | 2020-02-27 | 2022-09-20 | Amazon Technologies, Inc. | Segmentation using attention-weighted loss and discriminative feature learning |
| US11501107B2 (en) * | 2020-05-07 | 2022-11-15 | Adobe Inc. | Key-value memory network for predicting time-series metrics of target entities |
| US12505595B2 (en) | 2020-05-15 | 2025-12-23 | Nvidia Corporation | Content-aware style encoding using neural networks |
| JP7477864B2 (ja) * | 2020-05-18 | 2024-05-02 | 国立大学法人山梨大学 | 画像生成方法、プログラム及び画像生成装置 |
| CN111508048B (zh) * | 2020-05-22 | 2023-06-20 | 南京大学 | 一种可交互任意形变风格人脸漫画自动生成方法 |
| CN111833238B (zh) * | 2020-06-01 | 2023-07-25 | 北京百度网讯科技有限公司 | 图像的翻译方法和装置、图像翻译模型的训练方法和装置 |
| US11508051B2 (en) * | 2020-06-05 | 2022-11-22 | Leica Microsystems Cms Gmbh | Image and data analystics model compatibility regulation methods |
| CN111738910A (zh) * | 2020-06-12 | 2020-10-02 | 北京百度网讯科技有限公司 | 一种图像处理方法、装置、电子设备和存储介质 |
| US11574500B2 (en) * | 2020-09-08 | 2023-02-07 | Samsung Electronics Co., Ltd. | Real-time facial landmark detection |
| WO2022053431A1 (en) * | 2020-09-10 | 2022-03-17 | Interdigital Ce Patent Holdings, Sas | A method and an apparatus for generating a 3d face comprising at least one deformed region |
| US12333427B2 (en) | 2020-10-16 | 2025-06-17 | Adobe Inc. | Multi-scale output techniques for generative adversarial networks |
| KR102770927B1 (ko) * | 2020-11-04 | 2025-02-19 | 서울대학교산학협력단 | 손실 산입 학습 방법, 그의 장치, 기록 매체 및 이를 적용한 전자 디바이스 |
| CN112991151B (zh) * | 2021-02-09 | 2022-11-22 | 北京字跳网络技术有限公司 | 图像处理方法、图像生成方法、装置、设备和介质 |
| US12136155B2 (en) * | 2021-02-15 | 2024-11-05 | Carnegie Mellon University | System and method for photorealistic image synthesis using unsupervised semantic feature disentanglement |
| WO2022243250A1 (en) * | 2021-05-18 | 2022-11-24 | Interdigital Ce Patent Holdings, Sas | A method and an apparatus for generating a 3d face comprising at least one deformed region |
| US12056849B2 (en) * | 2021-09-03 | 2024-08-06 | Adobe Inc. | Neural network for image style translation |
| CN113762165A (zh) * | 2021-09-09 | 2021-12-07 | 北京海航中软科技有限公司 | 一种嫌疑人识别追踪方法及系统 |
| US11900519B2 (en) * | 2021-11-17 | 2024-02-13 | Adobe Inc. | Disentangling latent representations for image reenactment |
| CN114359035B (zh) * | 2021-12-27 | 2025-08-12 | 中山大学 | 一种基于生成对抗网络的人体风格迁移方法、设备及介质 |
| US12450787B2 (en) | 2021-12-28 | 2025-10-21 | POSTECH Research and Business Development Foundation | Automatic caricature generating method and apparatus |
| KR102678473B1 (ko) * | 2021-12-28 | 2024-06-27 | 포항공과대학교 산학협력단 | 자동 캐리커처 생성 방법 및 장치 |
| US12361614B2 (en) * | 2021-12-30 | 2025-07-15 | Snap Inc. | Protecting image features in stylized representations of a source image |
| EP4457760A1 (en) * | 2021-12-30 | 2024-11-06 | Snap Inc. | Protecting image features in stylized representations of a source image |
| US20230267652A1 (en) * | 2022-02-24 | 2023-08-24 | Adobe Inc. | Generating artistic content from a text prompt or a style image utilizing a neural network model |
| US20230377324A1 (en) * | 2022-05-19 | 2023-11-23 | Nvidia Corporation | Multi-domain generative adversarial networks for synthetic data generation |
| US20240029321A1 (en) * | 2022-07-20 | 2024-01-25 | Canon Kabushiki Kaisha | Image processing method, image processing apparatus, storage medium, image processing system, method of generating machine learning model, and learning apparatus |
| US12249132B2 (en) * | 2022-07-27 | 2025-03-11 | Adobe Inc. | Adapting generative neural networks using a cross domain translation network |
| US12322027B2 (en) * | 2022-12-29 | 2025-06-03 | Snap Inc. | Avatar generation according to artistic styles |
| US12469217B2 (en) | 2022-12-29 | 2025-11-11 | Snap Inc. | Infinite-scale city synthesis |
| WO2024206542A1 (en) * | 2023-03-29 | 2024-10-03 | Arizona Board Of Regents On Behalf Of Arizona State University | Systems and methods for enhancing retinal color fundus images for retinopathy analysis |
| KR102636217B1 (ko) * | 2023-04-14 | 2024-02-14 | 고려대학교산학협력단 | 가중 국소변환을 이용한 3차원 데이터 증강 방법 및 이를 위한 장치 |
| US12591947B2 (en) | 2023-05-25 | 2026-03-31 | Samsung Electronics Co., Ltd. | Distortion-based image rendering |
| KR102636155B1 (ko) * | 2023-07-18 | 2024-02-13 | 주식회사 젠젠에이아이 | 콘텐츠 코드를 이용한 이미지 생성 방법 및 시스템 |
| KR102803181B1 (ko) * | 2023-11-09 | 2025-05-07 | 리벨리온 주식회사 | 마할라노비스 거리 기반의 지각 손실을 이용한 모델 훈련 방법 및 장치 |
| WO2025100630A1 (ko) * | 2023-11-09 | 2025-05-15 | 주식회사 사피온코리아 | 마할라노비스 거리 기반의 지각 손실을 이용한 모델 훈련 방법 및 장치 |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018092869A1 (ja) | 2016-11-21 | 2018-05-24 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | 符号化装置、復号装置、符号化方法及び復号方法 |
Family Cites Families (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7483553B2 (en) | 2004-03-29 | 2009-01-27 | Microsoft Corporation | Caricature exaggeration |
| US7660482B2 (en) * | 2004-06-23 | 2010-02-09 | Seiko Epson Corporation | Method and apparatus for converting a photo to a caricature image |
| CN102096934B (zh) | 2011-01-27 | 2012-05-23 | 电子科技大学 | 一种基于机器学习的人脸卡通画生成方法 |
| US10366306B1 (en) * | 2013-09-19 | 2019-07-30 | Amazon Technologies, Inc. | Item identification among item variations |
| US9646195B1 (en) * | 2015-11-11 | 2017-05-09 | Adobe Systems Incorporated | Facial feature liquifying using face mesh |
| CN106548208B (zh) | 2016-10-28 | 2019-05-28 | 杭州米绘科技有限公司 | 一种照片图像快速智能风格化方法 |
| US10916001B2 (en) * | 2016-11-28 | 2021-02-09 | Adobe Inc. | Facilitating sketch to painting transformations |
| US10474929B2 (en) * | 2017-04-25 | 2019-11-12 | Nec Corporation | Cyclic generative adversarial network for unsupervised cross-domain image generation |
| US10504267B2 (en) * | 2017-06-06 | 2019-12-10 | Adobe Inc. | Generating a stylized image or stylized animation by matching semantic features via an appearance guide, a segmentation guide, and/or a temporal guide |
| US10565757B2 (en) * | 2017-06-09 | 2020-02-18 | Adobe Inc. | Multimodal style-transfer network for applying style features from multi-resolution style exemplars to input images |
| US10430455B2 (en) * | 2017-06-09 | 2019-10-01 | Adobe Inc. | Sketch and style based image retrieval |
| CN109426858B (zh) * | 2017-08-29 | 2021-04-06 | 京东方科技集团股份有限公司 | 神经网络、训练方法、图像处理方法及图像处理装置 |
| US10748314B2 (en) * | 2018-02-15 | 2020-08-18 | Microsoft Technology Licensing, Llc | Controllable conditional image generation |
| CN108257195A (zh) * | 2018-02-23 | 2018-07-06 | 深圳市唯特视科技有限公司 | 一种基于几何对比生成对抗网络的面部表情合成方法 |
| CN108596024B (zh) * | 2018-03-13 | 2021-05-04 | 杭州电子科技大学 | 一种基于人脸结构信息的肖像生成方法 |
| EP3605465B1 (en) * | 2018-07-30 | 2020-12-30 | Siemens Healthcare GmbH | A method for determining a correspondence between a source image and a reference image |
| US11430084B2 (en) * | 2018-09-05 | 2022-08-30 | Toyota Research Institute, Inc. | Systems and methods for saliency-based sampling layer for neural networks |
| CN111127304B (zh) * | 2018-10-31 | 2024-02-20 | 微软技术许可有限责任公司 | 跨域图像转换 |
| KR102708715B1 (ko) * | 2018-11-16 | 2024-09-24 | 삼성전자주식회사 | 영상 처리 장치 및 그 동작방법 |
| WO2020117975A1 (en) * | 2018-12-04 | 2020-06-11 | IsoPlexis Corporation | Systems, devices and methods for identification, selective ablation, and selection and collection of single cells |
| CN112926372B (zh) * | 2020-08-22 | 2023-03-10 | 清华大学 | 基于序列变形的场景文字检测方法及系统 |
-
2018
- 2018-10-31 CN CN201811294026.6A patent/CN111127304B/zh active Active
-
2019
- 2019-09-05 EP EP19769358.3A patent/EP3874458A1/en active Pending
- 2019-09-05 JP JP2021512501A patent/JP7373554B2/ja active Active
- 2019-09-05 WO PCT/US2019/049619 patent/WO2020091891A1/en not_active Ceased
- 2019-09-05 US US17/278,652 patent/US11481869B2/en active Active
- 2019-09-05 KR KR1020217013184A patent/KR102663519B1/ko active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018092869A1 (ja) | 2016-11-21 | 2018-05-24 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | 符号化装置、復号装置、符号化方法及び復号方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR102663519B1 (ko) | 2024-05-03 |
| CN111127304A (zh) | 2020-05-08 |
| KR20210083276A (ko) | 2021-07-06 |
| JP2022503647A (ja) | 2022-01-12 |
| WO2020091891A1 (en) | 2020-05-07 |
| US11481869B2 (en) | 2022-10-25 |
| CN111127304B (zh) | 2024-02-20 |
| EP3874458A1 (en) | 2021-09-08 |
| US20220044352A1 (en) | 2022-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7373554B2 (ja) | クロスドメイン画像変換 | |
| US11775829B2 (en) | Generative adversarial neural network assisted video reconstruction | |
| US11625613B2 (en) | Generative adversarial neural network assisted compression and broadcast | |
| US20250182404A1 (en) | Four-dimensional object and scene model synthesis using generative models | |
| CN114339409B (zh) | 视频处理方法、装置、计算机设备及存储介质 | |
| CN112233212A (zh) | 人像编辑与合成 | |
| CN113822965B (zh) | 图像渲染处理方法、装置和设备及计算机存储介质 | |
| CN113688907A (zh) | 模型训练、视频处理方法,装置,设备以及存储介质 | |
| JP2023545052A (ja) | 画像処理モデルの訓練方法及び装置、画像処理方法及び装置、電子機器並びにコンピュータプログラム | |
| US12406422B2 (en) | 3D digital avatar generation from a single or few portrait images | |
| US20250200896A1 (en) | Coherent three-dimensional portrait reconstruction via undistorting and fusing triplane representations | |
| CN116452715A (zh) | 动态人手渲染方法、装置及存储介质 | |
| Younis et al. | Sparse-view 3D reconstruction: Recent advances and open challenges | |
| US20230177722A1 (en) | Apparatus and method with object posture estimating | |
| CN120318380A (zh) | 三维图像生成方法和装置 | |
| CN116630744A (zh) | 图像生成模型训练方法及图像生成方法、装置及介质 | |
| Ahmadi et al. | Parameter efficient face frontalization in image sequences via GAN inversion | |
| US20250131680A1 (en) | Feature extraction with three-dimensional information | |
| US20250111610A1 (en) | Multimodal three-dimensional asset search techniques | |
| CN115908975B (zh) | 色彩预测模型训练方法、装置以及设备 | |
| US20260094363A1 (en) | Not-so-optimal transport flows for three-dimensional point cloud generation | |
| US20250111474A1 (en) | Sampling technique to scale neural volume rendering to high resolution | |
| US20260101026A1 (en) | High-quality three dimensional asset generation | |
| CN116385643B (zh) | 虚拟形象生成、模型的训练方法、装置及电子设备 | |
| US20260109034A1 (en) | Systems and methods for providing synthetic spatial imagination |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20220808 |
|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20220808 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20230926 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20231023 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 7373554 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |