Abstract: An image is rendered based a neural radiance field (NeRF) volumetric representation of a scene, where the NeRF representation is based on captured frames of video data, each frame including a color image, a widefield IR image, and a plurality of depth IR images of the scene. Each depth IR image is captured when the scene is illuminated by a different pattern of points of IR light, and the illumination by the patterns occurs at different times. The NeRF representation provides a mapping between positions and viewing directions to a color and optical density at each position in the scene, where the color and optical density at each position enables a viewing of the scene from a new perspective, and the NeRF representation provides a mapping between positions and viewing directions to IR values for each of the different patterns of points of IR light from the new perspective.

Abstract: The invention provides an integrated solution to the processing of the major portion of household waste comprising organic matter and plastics in an integrated way that produces useful products from both streams.

Abstract: Techniques of image synthesis using a neural radiance field (NeRF) includes generating a deformation model of movement experienced by a subject in a non-rigidly deforming scene. For example, when an image synthesis system uses NeRFs, the system takes as input multiple poses of subjects for training data. In contrast to conventional NeRFs, the technical solution first expresses the positions of the subjects from various perspectives in an observation frame. The technical solution then involves deriving a deformation model, i.e., a mapping between the observation frame and a canonical frame in which the subject's movements are taken into account. This mapping is accomplished using latent deformation codes for each pose that are determined using a multilayer perceptron (MLP). A NeRF is then derived from positions and casted ray directions in the canonical frame using another MLP. New poses for the subject may then be derived using the NeRF.

Abstract: A pallet top deck, a bottom deck, and spaced apart support blocks coupled between the top and bottom decks. Each support block includes an inner wall surrounding an interior opening, an outer wall surrounding the inner wall, and a plurality of ribs extending between the inner and outer walls. First and second upper tabs extend outwards from upper surfaces of the inner wall, with each upper tab comprising an angled contact surface for engaging the top deck. The angled contact surfaces of the first and second upper tabs are oriented in a first direction. First and second lower tabs extend outwards from lower surfaces of the ribs, with each tab comprising an angled contact surface for engaging the bottom deck. The angled contact surfaces of the first and second lower tabs are oriented in a second direction that is orthogonal to the first direction.

Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of depth views of an object, each of the plurality of depth views being captured from a respective viewpoint of the object, each of the plurality of depth views including respective depth data associated with a depth image of the object captured from the respective viewpoint, performing an aggregation operation on the plurality of depth views, and generating an image of the object from a target viewpoint based on the updated depth views, the target viewpoint being different from each of the respective viewpoints from which each of the plurality of depth views are captured.

Abstract: A pallet top deck, a bottom deck, and spaced apart support blocks coupled between the top and bottom decks. Each support block includes an inner wall surrounding an interior opening, an outer wall surrounding the inner wall, and a plurality of ribs extending between the inner and outer walls. First and second upper tabs extend outwards from upper surfaces of the inner wall, with each upper tab comprising an angled contact surface for engaging the top deck. The angled contact surfaces of the first and second upper tabs are oriented in a first direction. First and second lower tabs extend outwards from lower surfaces of the ribs, with each tab comprising an angled contact surface for engaging the bottom deck. The angled contact surfaces of the first and second lower tabs are oriented in a second direction that is orthogonal to the first direction.

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 are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.

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 three-dimensional object category modeling can utilize figure-ground neural radiance fields for unsupervised training and inference. For example, the systems and methods can include a foreground model and a background model that can generate an object output based at least in part on one or more learned embeddings. The foreground model and background model may process position data and view direction data in order to output color data and volume density data for a respective position and view direction. Moreover, the object category model may be trained to generate an object output, which may include an instance interpolation, a view synthesis, or a segmentation.

Abstract: Systems and methods are described for receiving a plurality of input images, a plurality of depth images, and a plurality of view parameters for generating a virtual view of a target subject. The systems and methods may generate a plurality of warped images based on the plurality of input images, the plurality of view parameters, and at least one of the plurality of depth images. In response to providing the plurality of depth images, the plurality of view parameters, and the plurality of warped images to a neural network, the systems and methods may receive, from the neural network, blending weights for assigning color to pixels of the virtual view of the target subject and may generate, based on the blending weights and the virtual view, a synthesized image according to the view parameters.

Abstract: A method and to a device for processing a 3D point cloud representing surroundings, which is generated by a sensor. Initially, starting cells are identified based on ascertained starting ground points within the 3D point cloud which meet at least one predefined ground point criterion with respect to a reference plane divided into cells. Thereafter, cell planes are ascertained for the respective starting cells of the reference plane. Thereafter, estimated cell planes and ground points are ascertained for candidate cells deviating from the starting cells based on the cell planes of the starting cells, which are subsequently converted into final cell planes. As a result of such a cell growth originating from the starting cells, the cells of the reference plane are iteratively run through and processed so that the 3D point cloud is reliably classifiable into ground points and object points based on this method.

Abstract: A method for range determination for a LIDAR sensor. The method includes: receiving measured values of a LIDAR sensor organized in a point cloud, and each including pieces of directional information and radial distance information relative to the LIDAR sensor and representing a laser beam reflected from the particular direction and at the particular radial distance; assigning the measured values based on the pieces of directional and radial distance information to areas of interest of a field of view; ascertaining a maximum distance range as an area of interest including a maximum radial distance to the LIDAR sensor and a point distribution of measured values of the area of interest, which includes a variance which reaches or exceeds a predetermined limiting value; and providing a value of the radial distance of the maximum distance range to the LIDAR sensor as the maximum range of the LIDAR sensor.

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: A pallet top deck, a bottom deck, and spaced apart support blocks coupled between the top and bottom decks. Each support block includes an inner wall surrounding an interior opening, an outer wall surrounding the inner wall, and a plurality of ribs extending between the inner and outer walls. First and second upper tabs extend outwards from upper surfaces of the inner wall, with each upper tab comprising an angled contact surface for engaging the top deck. The angled contact surfaces of the first and second upper tabs are oriented in a first direction. First and second lower tabs extend outwards from lower surfaces of the ribs, with each tab comprising an angled contact surface for engaging the bottom deck. The angled contact surfaces of the first and second lower tabs are oriented in a second direction that is orthogonal to the first direction.

Abstract: A method includes receiving a first image including color data and depth data, determining a viewpoint associated with an augmented reality (AR) and/or virtual reality (VR) display displaying a second image, receiving at least one calibration image including an object in the first image, the object being in a different pose as compared to a pose of the object in the first image, and generating the second image based on the first image, the viewpoint and the at least one calibration image.

Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

Abstract: Disclosed are super-hydrophobic, super oleophilic membranes comprising a metal mesh comprising copper, a coating comprising a carbohydrate derivative, wherein the carbohydrate derivative is covalently or ionically bonded to a metal mesh surface and methods of preparation thereof. The disclosed membranes are useful for wastewater treatment in the oil industry, in particular for oil/water separation processes.

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: A pallet includes a top deck, a bottom deck, and spaced apart support blocks coupled between the top and bottom decks and forming an opening therebetween for receiving a lifting member. The top deck includes at least one deck scoop area on an underside thereof. A thickness of the top deck is reduced in the at least one deck scoop area to reduce influence of top deck deflection on ability of the lifting member to pass through the opening between the top and bottom decks.