公开(公告)号：US20220215510A1

公开(公告)日：2022-07-07

申请号：US17557330

申请日：2021-12-21

Applicant: DASSAULT SYSTEMES

Inventor： Andreas WEINMANN ,  Holger DAMMERTZ

IPC: G06T5/00 ,  G06T3/40 ,  G06T5/50

Abstract: A computer-implemented method for forming a dataset configured for learning a Convolutional Neural Network (CNN) architecture including an image feature extractor. It comprises providing pairs of images, each pair comprising a reference image and a respective denoised image. For each pair of images, the method provides the pair of images to a pre-trained CNN architecture similar to the one the formed dataset will be configured for. The method computes an error map representing a difference between a first normalized feature of the denoised image and a second normalized feature of the reference image, the first and second normalized features being the output of a same layer of the pre-trained CNN architecture and adds the respective denoised image and the error map to the dataset. This constitutes an improved solution with respect to forming a dataset for learning a CNN architecture to identify areas of degradation generated by a denoiser.

公开(公告)号：US20240153212A1

公开(公告)日：2024-05-09

申请号：US18502818

申请日：2023-11-06

Applicant: DASSAULT SYSTEMES DEUTSCHLAND GMBH

Inventor： Andreas WEINMANN ,  Holger DAMMERTZ

IPC: G06T17/20 ,  G06V10/56 ,  H04N13/275

CPC classification number: G06T17/20 ,  G06V10/56 ,  H04N13/275

Abstract: This disclosure notably relates to a computer-implemented method for forming a dataset configured for learning a neural network architecture configured for inferring missing image details of a point cloud rendering. The method comprises the steps of obtaining a 3D mesh scene, computing a point cloud representation of the 3D mesh scene, generating one or more camera views of the 3D mesh scene and the point cloud representation. For each camera view, the method renders a viewpoint of the point cloud representation, of the 3D mesh scene, computes another point cloud representation of the viewpoint of the 3D mesh scene, and renders a viewpoint of the other point cloud representation. The method also comprises obtaining a pair of training samples, each comprising respectively the rendered viewpoint of the point cloud representation and the rendered viewpoint of the other point cloud representation; and adding the pair of training samples to the dataset.

公开(公告)号：US20220198612A1

公开(公告)日：2022-06-23

申请号：US17557326

申请日：2021-12-21

Applicant: Dassault Systemes

Inventor： Andreas WEINMANN ,  Holger DAMMERTZ

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A computer-implemented method of machine learning including learning a Convolutional Neural Network (CNN) architecture for estimating a degradation generated by a denoiser on a ray traced image. The method includes obtaining a dataset and learning the CNN architecture based on the obtained dataset. The learning including taking as input an image generated by the denoiser and a corresponding noisy image of the provided dataset and outputting an error map. This forms an improved solution with respect to estimating a degradation generated by a denoiser on a ray traced image.