-
公开(公告)号：WO2023090695A1
公开(公告)日：2023-05-25
申请号：PCT/KR2022/016955
申请日：2022-11-02
发明人： ABUOLAIM, Abdullah , PUNNAPPURATH, Abhijith , ABDELHAMED, Abdelrahman , BROWN, Michael Scott , LEVINSHTEIN, Aleksai
摘要： A method of generating a low-light image is provided. The method includes receiving a raw image, removing an amount of first illumination from the raw image, applying a low exposure condition to the raw image having the amount of first illumination removed, and applying an amount of low-light illumination to the raw image having the applied low exposure condition.
-
公开(公告)号：WO2023090596A1
公开(公告)日：2023-05-25
申请号：PCT/KR2022/013038
申请日：2022-08-31
申请人： ㈜플립션코리아
摘要： 얼굴 합성 방법 및 시스템이 제공된다. 얼굴 합성 방법은, 사용자로부터 사용자 얼굴 이미지를 수신하는 단계; 상기 사용자 얼굴 이미지로부터 윤곽 정보, 고유 정보 및 미세 정보를 포함하는 사용자 얼굴 정보를 추출하는 단계; 목표 얼굴 이미지와 비교하여, 상기 사용자 얼굴 정보 중 적어도 일부를 얼굴 합성에 사용할 정보로 선택하는 단계; 선택한 상기 적어도 일부의 상기 사용자 얼굴 정보를 이용하여 상기 사용자 얼굴 이미지와 상기 목표 얼굴 이미지를 합성하는 인공지능 얼굴 합성 모델을 학습시키는 단계; 사용자 얼굴이 포함된 원본 영상을 제공받는 단계; 상기 인공지능 얼굴 합성 모델을 이용하여, 상기 원본 영상의 프레임 별로 상기 사용자 얼굴에 목표 얼굴을 합성하는 단계; 및 합성이 완료된 상기 프레임으로부터 결과 영상을 생성하는 단계를 포함할 수 있다.
-
3.发明申请
公开(公告)号：WO2023083559A1
公开(公告)日：2023-05-19
申请号：PCT/EP2022/078619
申请日：2022-10-14
发明人： HOUBEN, Tim , PISARENCO, Maxim , HUISMAN, Thomas, Jarik , PU, Lingling , ZHOU, Jian , YU, Liangjiang , CHANG, Yi-Hsin , YEH, Yun- Ling
摘要： Systems and methods for image analysis include obtaining a plurality of simulation images and a plurality of non-simulation images both associated with a sample under inspection, at least one of the plurality of simulation images being a simulation image of a location on the sample not imaged by any of the plurality of non-simulation images; and training an unsupervised domain adaptation technique using the plurality of simulation images and the plurality of non-simulation images as inputs to reduce a difference between first intensity gradients of the plurality of simulation images and second intensity gradients of the plurality of non-simulation images.
-
公开(公告)号：WO2023083457A1
公开(公告)日：2023-05-19
申请号：PCT/EP2021/081469
申请日：2021-11-12
摘要： Described herein is an image processing apparatus (900) for forming an enhanced image, the apparatus being configured to: receive (801) one or more initial images (303); based on the received one or more initial images (303), implement (802) a first trained artificial intelligence model (301) to compute one or more capture parameters (307); receive (803) a set of images (306) captured using the one or more capture parameters (307); and implement (804) a second trained artificial intelligence model (302) to reconstruct an enhanced image (308) from the set of images (306). This may allow the apparatus to estimate capture parameters based on scene characteristics such as motion, distance to object and lighting, which may significantly reduce ghosting and exposure artefacts, increase reconstruction detail and reduce noise.
-
公开(公告)号：WO2023075885A1
公开(公告)日：2023-05-04
申请号：PCT/US2022/039652
申请日：2022-08-06
摘要： One example provides a computing device comprising a logic machine and a storage machine holding instructions executable by the logic machine to implement a depth image processing pipeline comprising a neural network, the neural network comprising an edge detecting layer. The neural network is configured to receive input of an active brightness image and receive input of one or more of real data or imaginary data of a complex depth image, the complex depth image corresponding to the active brightness image. The neural network is further configured to, at the edge detecting layer, apply one or more convolutional processes to the active brightness image to identify one or more edge pixels in the active brightness image, and at a second layer, denoise one or more of the real data or the imaginary data of the complex depth image based on the one or more edge pixels identified.
-
公开(公告)号：WO2023071841A1
公开(公告)日：2023-05-04
申请号：PCT/CN2022/125631
申请日：2022-10-17
申请人： 华为技术有限公司
摘要： 本申请实施例公开了图像处理方法、图像检测模型评估方法及装置，该图像处理方法包括：获取第一图像和第二图像；该第一图像叠加于该第二图像得到用于攻击图像检测模型的第三图像；基于第二图像中的部分区域即第一区域确定像素坐标参数的范围和角度参数的范围，像素坐标参数的范围为该第一区域在第二图像中的像素坐标的集合；基于该像素坐标参数的范围和角度参数的范围确定第一像素坐标集合和第一角度；该第一像素坐标集合指示第一图像叠加在第二图像上的位置，该第一角度指示叠加在第二图像上的第一图像的旋转角度。采用本申请实施例，可以获取攻击性较强、实用性较好的对抗样本以用于有效评估图像检测模型的鲁棒性。
-
公开(公告)号：WO2023060797A1
公开(公告)日：2023-04-20
申请号：PCT/CN2022/071604
申请日：2022-01-12
申请人： 东方晶源微电子科技（北京）有限公司
发明人： 陈晨
摘要： 一种用于半导体电子束缺陷监测的图像处理方法、装置和系统，方法包括步骤：S100、通过获取原图，对原图进行滤波处理，获得滤波图像；S200、获取滤波图像，采用对齐算法将滤波图像进行对齐处理，获得模板图像；S300、将模板图像与预设参考图像进行图像减法运算，获得差值图像；S400、计算差值图像的方差，并将方差与预设值进行对比判断，获取并输出比对判断结果。该图像处理方法能够提高缺陷检测过程中图像对齐的成功率，由于滤波去掉图像对齐中不必要的细节，再利用差值图像对对齐结果进行准确判断，进而可以交叉使用多种对齐算法，发挥各自优势，从而提升对齐算法的准确率。
-
公开(公告)号：WO2023047799A1
公开(公告)日：2023-03-30
申请号：PCT/JP2022/029221
申请日：2022-07-29
申请人： 富士フイルム株式会社
发明人： 林 伸治
摘要： 撮影対象範囲の空間上の位置と撮影画像との高精度な位置合わせが可能な画像処理装置、画像処理方法及びプログラムを提供する。１つ以上のプロセッサは、カメラを用いて撮影された撮影画像を取得し、撮影対象範囲の空間上における複数の特定点の位置を示す３次元の位置情報を取得し、撮影画像の撮影条件に基づいて、３次元の位置情報を２次元の画像座標に変換する透視投影変換のパラメータの値を設定し、透視投影変換を用いて複数の特定点の位置情報を画像座標のデータに変換し、変換により得られた画像座標のデータを基に抽出される第１の線分と、撮影画像から抽出される第２の線分との一致度を評価し、透視投影変換のパラメータの値を変更して一致度の評価を複数回実施し、複数回実施した評価の結果に基づいて、撮影画像と複数の特定点の位置との対応付けを行う。
-
公开(公告)号：WO2023031622A1
公开(公告)日：2023-03-09
申请号：PCT/GB2022/052248
申请日：2022-09-02
摘要： A system and method for generating sample data for analysis provide an image capture unit configured to capture a stack of images in image layers through a thickness of a sample, each image layer comprising pixel data in two orthogonal planes across the sample at a given sample depth; a processing unit configured: a) to process the captured pixel data to determine therefrom a pixel value of the energy of each pixel of the image, b) to select from each group of pixels through the stack of images the pixel having a highest energy; and c) to generate an output image file comprising a set of pixel data obtained from the selected pixels, wherein the output image file comprises for each pixel, the pixel position in the two orthogonal planes, the pixel vale and the depth position of the pixel in the image stack. The depth position of the selected pixel is provided in a fourth channel of the output image file, which represents a topography of a sample. An analysis unit comprises an input for receiving the output image file and to determine therefrom sample data, including identification of constituents in the sample and/or quantity of said constituents in the sample; and preferably comprises an artificial intelligence.
-
公开(公告)号：WO2023028866A1
公开(公告)日：2023-03-09
申请号：PCT/CN2021/115770
申请日：2021-08-31
申请人： 华为技术有限公司
发明人： 张毅
IPC分类号： G06T5/50
摘要： 本申请提供了一种图像处理方法、装置和车辆，涉及人工智能、自动驾驶、计算机视觉等领域。其中，该方法主要应用于卷积神经网络模型，该方法包括：获取当前帧RAW图；确定当前帧RAW图的第一特征；解析当前帧RAW图的上下文特征信息，该上下文特征信息包括局部特征信息和全局特征信息；根据局部特征信息和全局特征信息确定第一特征中的局部特征和全局特征；融合全局特征和局部特征，得到当前帧RAW图的特征融合图。本申请方案能够降低图像处理过程中算法的复杂度。
-
-
-
-
-
-
-
-
-
搜索结果
1733 条记录 (耗时 0.038 秒)
