公开(公告)号：US20240177269A1

公开(公告)日：2024-05-30

申请号：US18518614

申请日：2023-11-24

申请人： MEDIATEK INC.

发明人： Jie-En Yao ,  Yi-Chen Lo ,  Li-Yuan Tsao ,  Shou-Yao Tseng ,  Chia-Che Chang ,  Chun-Yi Lee

IPC分类号： G06T3/40

CPC分类号： G06T3/4053 ,  G06T3/4046

摘要： A method of local implicit normalizing flow for arbitrary-scale image super-resolution, an associated apparatus and an associated computer-readable medium are provided. The method applicable to a processing circuit may include: utilizing the processing circuit to run a local implicit normalizing flow framework to start performing arbitrary-scale image super-resolution with a trained model of the local implicit normalizing flow framework according to at least one input image, for generating at least one output image, where a selected scale of the output image with respect to the input image is an arbitrary-scale; and during performing the arbitrary-scale image super-resolution with the trained model, performing prediction processing to obtain multiple super-resolution predictions for different locations of a predetermined space in a situation where a same non-super-resolution input image among the at least one input image is given, in order to generate the at least one output image.

公开(公告)号：US12079306B2

公开(公告)日：2024-09-03

申请号：US17529539

申请日：2021-11-18

申请人： MEDIATEK INC.

发明人： Yi-Chen Lo ,  Chia-Che Chang

IPC分类号： G06T7/90 ,  G06F18/214 ,  G06F18/22 ,  G06N20/00 ,  G06V10/40 ,  G06V10/56 ,  H04N9/73

CPC分类号： G06F18/214 ,  G06F18/22 ,  G06N20/00 ,  G06T7/90 ,  G06V10/40 ,  G06V10/56 ,  H04N9/73 ,  G06T2207/10152 ,  G06T2207/20081 ,  G06T2207/20084

摘要： A contrastive learning method for color constancy employs a fully-supervised construction of contrastive pairs, driven by a novel data augmentation. The contrastive learning method includes receiving two training images, constructing positive and negative contrastive pairs by the novel data augmentation, extracting representations by a feature extraction function, and training a color constancy model by contrastive learning representations in the positive contrastive pair are closer than representations in the negative contrastive pair. The positive contrastive pair contains images having an identical illuminant while negative contrastive pair contains images having different illuminants. The contrastive learning method improves the performance without additional computational costs. The desired contrastive pairs allow the color constancy model to learn better illuminant feature that are particular robust to worse-cases in data sparse regions.

公开(公告)号：US20240177319A1

公开(公告)日：2024-05-30

申请号：US18518609

申请日：2023-11-24

申请人： MEDIATEK INC.

发明人： Ting-Hsuan Liao ,  Huang-Ru Liao ,  Shan-Ya Yang ,  Jie-En Yao ,  Li-Yuan Tsao ,  Hsu-Shen Liu ,  Bo-Wun Cheng ,  Chen-Hao Chao ,  Chia-Che Chang ,  Yi-Chen Lo ,  Chun-Yi Lee

IPC分类号： G06T7/12 ,  G06T7/13 ,  G06T9/00

CPC分类号： G06T7/12 ,  G06T7/13 ,  G06T9/00

摘要： Many unsupervised domain adaptation (UDA) methods have been proposed to bridge the domain gap by utilizing domain invariant information. Most approaches have chosen depth as such information and achieved remarkable successes. Despite their effectiveness, using depth as domain invariant information in UDA tasks may lead to multiple issues, such as excessively high extraction costs and difficulties in achieving a reliable prediction quality. As a result, we introduce Edge Learning based Domain Adaptation (ELDA), a framework which incorporates edge information into its training process to serve as a type of domain invariant information. Our experiments quantitatively and qualitatively demonstrate that the incorporation of edge information is indeed beneficial and effective, and enables ELDA to outperform the contemporary state-of-the-art methods on two commonly adopted benchmarks for semantic segmentation based UDA tasks. In addition, we show that ELDA is able to better separate the feature distributions of different classes.