Patents by Inventor Rene Ranftl
Rene Ranftl 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: 20240161387Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.Type: ApplicationFiled: October 6, 2023Publication date: May 16, 2024Inventors: Rene Ranftl, Vladlen Koltun
-
Patent number: 11816784Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.Type: GrantFiled: June 15, 2022Date of Patent: November 14, 2023Assignee: Intel CorporationInventors: Rene Ranftl, Vladlen Koltun
-
Publication number: 20220343521Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for metric depth estimation using a monocular visual-inertial system. An example apparatus for metric depth estimation includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to access a globally-aligned depth prediction, the globally-aligned depth prediction generated based on a monocular depth estimator, access a dense scale map scaffolding, the dense scale map scaffolding generated based on visual-inertial odometry, regress a dense scale residual map determined using the globally-aligned depth prediction and the dense scale map scaffolding, and apply the dense scale residual map to the globally-aligned depth prediction.Type: ApplicationFiled: June 30, 2022Publication date: October 27, 2022Inventors: Diana Wofk, Rene Ranftl, Matthias Mueller, Vladlen Koltun
-
Publication number: 20220309739Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.Type: ApplicationFiled: June 15, 2022Publication date: September 29, 2022Applicant: Intel CorporationInventors: Rene Ranftl, Vladlen Koltun
-
Patent number: 11393160Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.Type: GrantFiled: March 23, 2018Date of Patent: July 19, 2022Assignee: Intel CorporationInventors: Rene Ranftl, Vladlen Koltun
-
Publication number: 20220012848Abstract: Methods, apparatus, systems and articles of manufacture disclosed herein perform dense prediction of an input image using transformers at an encoder stage and at a reassembly stage of an image processing system. A disclosed apparatus includes an encoder with an embedder to convert an input image to a plurality of tokens representing features extracted from the input image. The tokens are embedded with a learnable position embedding. The encoder also includes one or more transformers configured in a sequence of stages to relate the tokens to each other. The apparatus further includes a decoder that includes one or more of reassemblers to assemble the tokens into feature representations, one or more of fusion blocks to combine the feature representations to generate a final feature representation, and an output head to generate a dense prediction based on the final feature representation and based on an output task.Type: ApplicationFiled: September 25, 2021Publication date: January 13, 2022Inventors: Rene Ranftl, Alexey Bochkovskiy, Vladlen Koltun
-
Patent number: 10467768Abstract: Techniques are provided for estimation of optical flow between images using 4-dimensional cost volume processing. A methodology implementing the techniques according to an embodiment includes extracting a first set of feature vectors from a first image and extracting a second set of feature vectors from a second image. Each feature vector of the first set is associated with a pixel of the first image and each feature vector of the second set is associated with a pixel of the second image. The method further includes constructing a 4-dimensional (4D) cost volume to store a distance metric between each feature vector of the first set of feature vectors and a selected subset of feature vectors of the second set of feature vectors. The method further includes performing a flow-semi-global matching (Flow-SGM) on the 4D cost volume to estimate an optical flow vector for pixels of the first image.Type: GrantFiled: April 7, 2017Date of Patent: November 5, 2019Assignee: INTEL CORPORATIONInventors: Jia Xu, René Ranftl, Vladlen Koltun
-
Publication number: 20190043244Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.Type: ApplicationFiled: March 23, 2018Publication date: February 7, 2019Applicant: Intel CorporationInventors: Rene Ranftl, Vladlen Koltun
-
Publication number: 20180293454Abstract: Techniques are provided for estimation of optical flow between images using 4-dimensional cost volume processing. A methodology implementing the techniques according to an embodiment includes extracting a first set of feature vectors from a first image and extracting a second set of feature vectors from a second image. Each feature vector of the first set is associated with a pixel of the first image and each feature vector of the second set is associated with a pixel of the second image. The method further includes constructing a 4-dimensional (4D) cost volume to store a distance metric between each feature vector of the first set of feature vectors and a selected subset of feature vectors of the second set of feature vectors. The method further includes performing a flow-semi-global matching (Flow-SGM) on the 4D cost volume to estimate an optical flow vector for pixels of the first image.Type: ApplicationFiled: April 7, 2017Publication date: October 11, 2018Applicant: INTEL CORPORATIONInventors: Jia Xu, René Ranftl, Vladlen Koltun