Patents by Inventor Jon Niklas Theodor Hasselgren
Jon Niklas Theodor Hasselgren 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).
-
Patent number: 11657571Abstract: Systems and methods enable optimization of a 3D model representation comprising the shape and appearance of a particular 3D scene or object. The opaque 3D mesh (e.g., vertex positions and corresponding topology) and spatially varying material attributes are jointly optimized based on image space losses to match multiple image observations (e.g., reference images of the reference 3D scene or object). A geometric topology defines faces and/or cells in the opaque 3D mesh that are visible and may be randomly initialized and optimized through training based on the image space losses. Applying the geometry topology to an opaque 3D mesh for learning the shape improves accuracy of silhouette edges and performance compared with using transparent mesh representations. In contrast with approaches that require an initial guess for the topology and/or an exhaustive testing of possible geometric topologies, the 3D model representation is learned based on image space differences without requiring an initial guess.Type: GrantFiled: December 13, 2022Date of Patent: May 23, 2023Assignee: NVIDIA CorporationInventors: Jon Niklas Theodor Hasselgren, Carl Jacob Munkberg
-
Publication number: 20230140460Abstract: A technique is described for extracting or constructing a three-dimensional (3D) model from multiple two-dimensional (2D) images. In an embodiment, a foreground segmentation mask or depth field may be provided as an additional supervision input with each 2D image. In an embodiment, the foreground segmentation mask or depth field is automatically generated for each 2D image. The constructed 3D model comprises a triangular mesh topology, materials, and environment lighting. The constructed 3D model is represented in a format that can be directly edited and/or rendered by conventional application programs, such as digital content creation (DCC) tools. For example, the constructed 3D model may be represented as a triangular surface mesh (with arbitrary topology), a set of 2D textures representing spatially-varying material parameters, and an environment map. Furthermore, the constructed 3D model may be included in 3D scenes and interacts realistically with other objects.Type: ApplicationFiled: May 30, 2022Publication date: May 4, 2023Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex John Bauld Evans, Thomas Müller-Höhne, Sanja Fidler
-
Publication number: 20230105025Abstract: Systems and methods enable optimization of a 3D model representation comprising the shape and appearance of a particular 3D scene or object. The opaque 3D mesh (e.g., vertex positions and corresponding topology) and spatially varying material attributes are jointly optimized based on image space losses to match multiple image observations (e.g., reference images of the reference 3D scene or object). A geometric topology defines faces and/or cells in the opaque 3D mesh that are visible and may be randomly initialized and optimized through training based on the image space losses. Applying the geometry topology to an opaque 3D mesh for learning the shape improves accuracy of silhouette edges and performance compared with using transparent mesh representations. In contrast with approaches that require an initial guess for the topology and/or an exhaustive testing of possible geometric topologies, the 3D model representation is learned based on image space differences without requiring an initial guess.Type: ApplicationFiled: December 13, 2022Publication date: April 6, 2023Inventors: Jon Niklas Theodor Hasselgren, Carl Jacob Munkberg
-
Patent number: 11615602Abstract: Appearance driven automatic three-dimensional (3D) modeling enables optimization of a 3D model comprising the shape and appearance of a particular 3D scene or object. Triangle meshes and shading models may be jointly optimized to match the appearance of a reference 3D model based on reference images of the reference 3D model. Compared with the reference 3D model, the optimized 3D model is a lower resolution 3D model that can be rendered in less time. More specifically, the optimized 3D model may include fewer geometric primitives compared with the reference 3D model. In contrast with the conventional inverse rendering or analysis-by-synthesis modeling tools, the shape and appearance representations of the 3D model are automatically generated that, when rendered, match the reference images.Type: GrantFiled: August 15, 2022Date of Patent: March 28, 2023Assignee: NVIDIA CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren
-
Patent number: 11610370Abstract: Systems and methods enable optimization of a 3D model representation comprising the shape and appearance of a particular 3D scene or object. The opaque 3D mesh (e.g., vertex positions and corresponding topology) and spatially varying material attributes are jointly optimized based on image space losses to match multiple image observations (e.g., reference images of the reference 3D scene or object). A geometric topology defines faces and/or cells in the opaque 3D mesh that are visible and may be randomly initialized and optimized through training based on the image space losses. Applying the geometry topology to an opaque 3D mesh for learning the shape improves accuracy of silhouette edges and performance compared with using transparent mesh representations. In contrast with approaches that require an initial guess for the topology and/or an exhaustive testing of possible geometric topologies, the 3D model representation is learned based on image space differences without requiring an initial guess.Type: GrantFiled: August 27, 2021Date of Patent: March 21, 2023Assignee: NVIDIA CorporationInventors: Jon Niklas Theodor Hasselgren, Carl Jacob Munkberg
-
Publication number: 20230014245Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.Type: ApplicationFiled: September 8, 2022Publication date: January 19, 2023Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Anjul Patney, Marco Salvi, Aaron Eliot Lefohn, Donald Lee Brittain
-
Patent number: 11557022Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.Type: GrantFiled: December 18, 2019Date of Patent: January 17, 2023Assignee: NVIDIA CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Anjul Patney, Marco Salvi, Aaron Eliot Lefohn, Donald Lee Brittain
-
Publication number: 20220405582Abstract: A method, computer readable medium, and system are disclosed for training a neural network model. The method includes the step of selecting an input vector from a set of training data that includes input vectors and sparse target vectors, where each sparse target vector includes target data corresponding to a subset of samples within an output vector of the neural network model. The method also includes the steps of processing the input vector by the neural network model to produce output data for the samples within the output vector and adjusting parameter values of the neural network model to reduce differences between the output vector and the sparse target vector for the subset of the samples.Type: ApplicationFiled: February 4, 2022Publication date: December 22, 2022Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Jaakko T. Lehtinen, Timo Oskari Aila
-
Publication number: 20220392160Abstract: Systems and methods enable optimization of a 3D model representation comprising the shape and appearance of a particular 3D scene or object. The opaque 3D mesh (e.g., vertex positions and corresponding topology) and spatially varying material attributes are jointly optimized based on image space losses to match multiple image observations (e.g., reference images of the reference 3D scene or object). A geometric topology defines faces and/or cells in the opaque 3D mesh that are visible and may be randomly initialized and optimized through training based on the image space losses. Applying the geometry topology to an opaque 3D mesh for learning the shape improves accuracy of silhouette edges and performance compared with using transparent mesh representations. In contrast with approaches that require an initial guess for the topology and/or an exhaustive testing of possible geometric topologies, the 3D model representation is learned based on image space differences without requiring an initial guess.Type: ApplicationFiled: August 27, 2021Publication date: December 8, 2022Inventors: Jon Niklas Theodor Hasselgren, Carl Jacob Munkberg
-
Publication number: 20220392179Abstract: Appearance driven automatic three-dimensional (3D) modeling enables optimization of a 3D model comprising the shape and appearance of a particular 3D scene or object. Triangle meshes and shading models may be jointly optimized to match the appearance of a reference 3D model based on reference images of the reference 3D model. Compared with the reference 3D model, the optimized 3D model is a lower resolution 3D model that can be rendered in less time. More specifically, the optimized 3D model may include fewer geometric primitives compared with the reference 3D model. In contrast with the conventional inverse rendering or analysis-by-synthesis modeling tools, the shape and appearance representations of the 3D model are automatically generated that, when rendered, match the reference images.Type: ApplicationFiled: August 15, 2022Publication date: December 8, 2022Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren
-
Patent number: 11475542Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.Type: GrantFiled: December 17, 2019Date of Patent: October 18, 2022Assignee: NVIDIA CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Anjul Patney, Marco Salvi, Aaron Eliot Lefohn, Donald Lee Brittain
-
Patent number: 11450077Abstract: Appearance driven automatic three-dimensional (3D) modeling enables optimization of a 3D model comprising the shape and appearance of a particular 3D scene or object. Triangle meshes and shading models may be jointly optimized to match the appearance of a reference 3D model based on reference images of the reference 3D model. Compared with the reference 3D model, the optimized 3D model is a lower resolution 3D model that can be rendered in less time. More specifically, the optimized 3D model may include fewer geometric primitives compared with the reference 3D model. In contrast with the conventional inverse rendering or analysis-by-synthesis modeling tools, the shape and appearance representations of the 3D model are automatically generated that, when rendered, match the reference images.Type: GrantFiled: March 8, 2021Date of Patent: September 20, 2022Assignee: NVIDIA CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren
-
Publication number: 20220165040Abstract: Appearance driven automatic three-dimensional (3D) modeling enables optimization of a 3D model comprising the shape and appearance of a particular 3D scene or object. Triangle meshes and shading models may be jointly optimized to match the appearance of a reference 3D model based on reference images of the reference 3D model. Compared with the reference 3D model, the optimized 3D model is a lower resolution 3D model that can be rendered in less time. More specifically, the optimized 3D model may include fewer geometric primitives compared with the reference 3D model. In contrast with the conventional inverse rendering or analysis-by-synthesis modeling tools, the shape and appearance representations of the 3D model are automatically generated that, when rendered, match the reference images.Type: ApplicationFiled: March 8, 2021Publication date: May 26, 2022Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren
-
Patent number: 11244226Abstract: A method, computer readable medium, and system are disclosed for training a neural network model. The method includes the step of selecting an input vector from a set of training data that includes input vectors and sparse target vectors, where each sparse target vector includes target data corresponding to a subset of samples within an output vector of the neural network model. The method also includes the steps of processing the input vector by the neural network model to produce output data for the samples within the output vector and adjusting parameter values of the neural network model to reduce differences between the output vector and the sparse target vector for the subset of the samples.Type: GrantFiled: January 26, 2018Date of Patent: February 8, 2022Assignee: NVIDIA CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Jaakko T. Lehtinen, Timo Oskari Aila
-
Publication number: 20210374384Abstract: Apparatuses, systems, and techniques to identify one or more layers of a three-dimensional graphical image to generate a two-dimensional representation. In at least one embodiment, one or more layers of a three-dimensional graphical image are identified to generate one or more two-dimensional representations.Type: ApplicationFiled: June 2, 2020Publication date: December 2, 2021Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren
-
Patent number: 10970816Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.Type: GrantFiled: May 24, 2019Date of Patent: April 6, 2021Assignee: Nvidia CorporationInventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Marco Salvi
-
Publication number: 20200126191Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.Type: ApplicationFiled: December 17, 2019Publication date: April 23, 2020Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Anjul Patney, Marco Salvi, Aaron Eliot Lefohn, Donald Lee Brittain
-
Publication number: 20200126192Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.Type: ApplicationFiled: December 18, 2019Publication date: April 23, 2020Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Anjul Patney, Marco Salvi, Aaron Eliot Lefohn, Donald Lee Brittain
-
Patent number: 10565686Abstract: A method, computer readable medium, and system are disclosed for training a neural network. The method includes the steps of selecting an input sample from a set of training data that includes input samples and noisy target samples, where the input samples and the noisy target samples each correspond to a latent, clean target sample. The input sample is processed by a neural network model to produce an output and a noisy target sample is selected from the set of training data, where the noisy target samples have a distribution relative to the latent, clean target sample. The method also includes adjusting parameter values of the neural network model to reduce differences between the output and the noisy target sample.Type: GrantFiled: November 8, 2017Date of Patent: February 18, 2020Assignee: NVIDIA CorporationInventors: Jaakko T. Lehtinen, Timo Oskari Aila, Jon Niklas Theodor Hasselgren, Carl Jacob Munkberg
-
Publication number: 20200051206Abstract: A neural network structure, namely a warped external recurrent neural network, is disclosed for reconstructing images with synthesized effects. The effects can include motion blur, depth of field reconstruction (e.g., simulating lens effects), and/or anti-aliasing (e.g., removing artifacts caused by sampling frequency). The warped external recurrent neural network is not recurrent at each layer inside the neural network. Instead, the external state output by the final layer of the neural network is warped and provided as a portion of the input to the neural network for the next image in a sequence of images. In contrast, in a conventional recurrent neural network, hidden state generated at each layer is provided as a feedback input to the generating layer. The neural network can be implemented, at least in part, on a processor. In an embodiment, the neural network is implemented on at least one parallel processing unit.Type: ApplicationFiled: May 24, 2019Publication date: February 13, 2020Inventors: Carl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Marco Salvi