Abstract: Systems and methods for training a neural radiance field model can include the use of image patches for ground truth training. For example, the systems and methods can include generating patch renderings with a neural radiance field model, comparing the patch renderings to ground truth patches from ground truth images, and adjusting one or more parameters based on the comparison. Additionally and/or alternatively, the systems and methods can include the utilization of a flow model for mitigating and/or minimizing artifact generation.

Abstract: Example embodiments of the present disclosure provide an example computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs. The example method includes obtaining, by a computing system comprising one or more processors, an image set comprising one or more views of a subject scene. The example method includes generating, by the computing system and based at least in part on the image set, a scene representation describing the subject scene in three dimensions. The example method includes generating, by the computing system and using a machine-learned semantic segmentation model framework, a multidimensional field of probability distributions over semantic categories, the multidimensional field defined over the three dimensions of the subject scene. The example method includes outputting, by the computing system, classification data for at least one location in the subject scene.

Abstract: Systems and methods for training a neural radiance field model can include the use of image patches for ground truth training. For example, the systems and methods can include generating patch renderings with a neural radiance field model, comparing the patch renderings to ground truth patches from ground truth images, and adjusting one or more parameters based on the comparison. Additionally and/or alternatively, the systems and methods can include the utilization of a flow model for mitigating and/or minimizing artifact generation.

Abstract: Provided are machine learning models that generate geometry-free neural scene representations through efficient object-centric novel-view synthesis. In particular, one example aspect of the present disclosure provides a novel framework in which an encoder model (e.g., an encoder transformer network) processes one or more RGB images (with or without pose) to produce a fully latent scene representation that can be passed to a decoder model (e.g., a decoder transformer network). Given one or more target poses, the decoder model can synthesize images in a single forward pass. In some example implementations, because transformers are used rather than convolutional or MLP networks, the encoder can learn an attention model that extracts enough 3D information about a scene from a small set of images to render novel views with correct projections, parallax, occlusions, and even semantics, without explicit geometry.

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

Abstract: Systems and methods for training a neural radiance field model can include the use of image patches for ground truth training. For example, the systems and methods can include generating patch renderings with a neural radiance field model, comparing the patch renderings to ground truth patches from ground truth images, and adjusting one or more parameters based on the comparison. Additionally and/or alternatively, the systems and methods can include the utilization of a flow model for mitigating and/or minimizing artifact generation.

Abstract: Example embodiments of the present disclosure provide an example computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs. The example method includes obtaining, by a computing system comprising one or more processors, an image set comprising one or more views of a subject scene. The example method includes generating, by the computing system and based at least in part on the image set, a scene representation describing the subject scene in three dimensions. The example method includes generating, by the computing system and using a machine-learned semantic segmentation model framework, a multidimensional field of probability distributions over semantic categories, the multidimensional field defined over the three dimensions of the subject scene. The example method includes outputting, by the computing system, classification data for at least one location in the subject scene.

Abstract: Provided are machine learning models that generate geometry-free neural scene representations through efficient object-centric novel-view synthesis. In particular, one example aspect of the present disclosure provides a novel framework in which an encoder model (e.g., an encoder transformer network) processes one or more RGB images (with or without pose) to produce a fully latent scene representation that can be passed to a decoder model (e.g., a decoder transformer network). Given one or more target poses, the decoder model can synthesize images in a single forward pass. In some example implementations, because transformers are used rather than convolutional or MLP networks, the encoder can learn an attention model that extracts enough 3D information about a scene from a small set of images to render novel views with correct projections, parallax, occlusions, and even semantics, without explicit geometry.

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).