Patents by Inventor Andreas Weinmann
Andreas Weinmann has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20250225705Abstract: Systems and methods are provided for a neural network for frame interpolation. The systems and methods can be used in real time applications such as gaming platforms, and include receiving two consecutive input image frames and a motion vector, and warping the input image frames to generate an intermediate frame at a new timepoint that lies between the two input image frames. A first network generates optical flow data representing changes between the two consecutive input image frames, such as changes in illumination and/or shading. The system generates optical flow data from each input image frame to the new timepoint as well as motion vectors from each input image to the new timepoint. A second network can use the optical flow data and the motion vector data to generate the intermediate frame. The frame interpolation pipeline can generate intermediate frames in an interactive environment where future frames are unknown.Type: ApplicationFiled: March 27, 2025Publication date: July 10, 2025Inventors: Dmitry Kozlov, Lorenzo Tessari, Andreas Weinmann, Oliver Simons, Mikhail Petrushkov, Vladimir Travkin
-
Patent number: 12094091Abstract: 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.Type: GrantFiled: December 21, 2021Date of Patent: September 17, 2024Assignee: Dassault SystemsInventors: Andreas Weinmann, Holger Dammertz
-
Publication number: 20240153212Abstract: 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.Type: ApplicationFiled: November 6, 2023Publication date: May 9, 2024Applicant: DASSAULT SYSTEMES DEUTSCHLAND GMBHInventors: Andreas WEINMANN, Holger DAMMERTZ
-
Patent number: 11786954Abstract: A method of expanding an elongated and at least regionally planar metal element that has two respective marginal regions oppositely disposed and extending in a longitudinal direction and a central region arranged therebetween and including cuts, the marginal regions of the metal element are moved apart transversely to the longitudinal direction and in parallel with a planar extent of the metal element such that connection portions of the central region formed by the cuts and connecting the two respective marginal regions to one another are folded, the method includes displacing the two respective marginal regions with respect to one another transversely to the planar extent of the metal element to form a displaced state, and subsequently moving apart the two respective marginal regions in the displaced state.Type: GrantFiled: December 13, 2017Date of Patent: October 17, 2023Assignee: PROTEKTORWERK FLORENZ MAISCH GMBH & CO. KGInventors: Heiner Willerscheid, Andreas Weinmann
-
Publication number: 20220215510Abstract: 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.Type: ApplicationFiled: December 21, 2021Publication date: July 7, 2022Applicant: DASSAULT SYSTEMESInventors: Andreas WEINMANN, Holger DAMMERTZ
-
Publication number: 20220198612Abstract: 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.Type: ApplicationFiled: December 21, 2021Publication date: June 23, 2022Applicant: Dassault SystemesInventors: Andreas WEINMANN, Holger DAMMERTZ
-
Publication number: 20190337039Abstract: A method of expanding an elongated and at least regionally planar metal element that has two respective marginal regions oppositely disposed and extending in a longitudinal direction and a central region arranged therebetween and including cuts, the marginal regions of the metal element are moved apart transversely to the longitudinal direction and in parallel with a planar extent of the metal element such that connection portions of the central region formed by the cuts and connecting the two respective marginal regions to one another are folded, the method includes displacing the two respective marginal regions with respect to one another transversely to the planar extent of the metal element to form a displaced state, and subsequently moving apart the two respective marginal regions in the displaced state.Type: ApplicationFiled: December 13, 2017Publication date: November 7, 2019Inventors: Heiner WILLERSCHEID, Andreas WEINMANN
-
Publication number: 20110274923Abstract: The invention relates to an extrusion system for producing cylindrical semi-finished plastic products. The extrusion system comprises an extruder (1) for making available a pressurized plastic melt, at least one extrusion die (7) arranged on the extruder (1) and allowing the melt to leave the extruder (1) as a substantially cylindrical plastic strand (8), a calibration unit (2) which is mounted downstream of the extrusion die (7) and through which the freshly extruded plastic strand (8) passes, said calibration unit cooling the plastic strand (8) and giving it an outer diameter (d), a brake device (3) mounted downstream of the calibration unit (2) and adapted to introduce a variable axial force (A) into the plastic strand (8), said axial force being opposite to the advance of the plastic strand, and a force transducer (9) measuring the axial force (A) introduced into the plastic strand (8) by the brake device (3).Type: ApplicationFiled: January 18, 2010Publication date: November 10, 2011Applicant: EVONIK DEGUSSA GMBHInventors: Markus Hartmann, Rainer Goering, Andreas Weinmann, Sascha Kottmann
-
Publication number: 20050212164Abstract: A caterpillar take-off device for hauling off extrusion products, in particular plastic tubes, includes at least two caterpillar tracks arranged symmetrically in relation to a length axis of the caterpillar take-off device, at least during take-off process by changing the distance from the caterpillar tracks to the length axis. In the event of a change in cross-section of the extrusion product, the change is measured and the distance of the caterpillar tracks from the length axis is automatically adjusted such that the symmetry axis of the extrusion product coincides with the longitudinal axis of the caterpillar take-off unit.Type: ApplicationFiled: February 22, 2005Publication date: September 29, 2005Applicant: KRAUSS-MAFFEI KUNSTSTOFFTECHNIK GMBHInventors: Henning Stieglitz, Roman Laberer, Stefan Jovers, Andreas Weinmann, Karl-Heinz Forsch, Karl-Heinz Baston