Abstract: Methods for motion-controllable video diffusion include extracting optical flow fields from an input video and computing warped noise by iteratively warping noise between consecutive frames using the optical flow fields. The iteratively warping includes (i) re-Gaussianizing expanded pixel regions by sampling fresh Gaussian noise, and (ii) aggregating contracted pixel regions by merging noise particles and renormalizing variance to preserve spatial Gaussianity. An output video is generated by initializing a diffusion process with the warped noise and iteratively denoising to produce temporally coherent output frames. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Example embodiments relate to techniques for volumetric performance capture with neural rendering. A technique may involve initially obtaining images that depict a subject from multiple viewpoints and under various lighting conditions using a light stage and depth data corresponding to the subject using infrared cameras. A neural network may extract features of the subject from the images based on the depth data and map the features into a texture space (e.g., the UV texture space). A neural renderer can be used to generate an output image depicting the subject from a target view such that illumination of the subject in the output image aligns with the target view. The neural render may resample the features of the subject from the texture space to an image space to generate the output image.

Abstract: Apparatus and methods related to applying lighting models to images are provided. An example method includes receiving, via a computing device, an image comprising a subject. The method further includes relighting, via a neural network, a foreground of the image to maintain a consistent lighting of the foreground with a target illumination. The relighting is based on a per-pixel light representation indicative of a surface geometry of the foreground. The light representation includes a specular component, and a diffuse component, of surface reflection. The method additionally includes predicting, via the neural network, an output image comprising the subject in the relit foreground. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: A system includes a first structure that houses first cameras, where each camera is controllably moveable in synchronization with second cameras on a second structure and with third cameras on a third, overhead structure. The first, second, and third sets of cameras are controllably directed toward a specified entity. The second set of cameras are controllably moveable in synchronization with the first and third sets of cameras, and the third, overhead cameras are controllably moveable in synchronization with the first and second sets of cameras. The system also includes a controller configured to generate and send control signals to the first, second, and third sets of cameras to track the specified entity as the specified entity moves within a defined space that is observable by the first, second, and third sets of cameras in the first, second, and third structures. Various other apparatuses and devices are also disclosed.

Abstract: Example embodiments relate to techniques for volumetric performance capture with neural rendering. A technique may involve initially obtaining images that depict a subject from multiple viewpoints and under various lighting conditions using a light stage and depth data corresponding to the subject using infrared cameras. A neural network may extract features of the subject from the images based on the depth data and map the features into a texture space (e.g., the UV texture space). A neural renderer can be used to generate an output image depicting the subject from a target view such that illumination of the subject in the output image aligns with the target view. The neural render may resample the features of the subject from the texture space to an image space to generate the output image.

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: Apparatus and methods related to light redistribution in images are provided. An example method includes receiving, by a computing device, an input image comprising a subject. The method further includes adjusting, by a neural network, one or more of a specular component or a diffuse component associated with the input image. The adjusting involves redistributing a per-pixel light energy of the input image. The method additionally includes predicting, by the neural network, an output image comprising the subject with the adjusted one or more of the specular component or the diffuse component.

Abstract: An example method, apparatus, and computer-readable storage medium are provided to predict high-dynamic range (HDR) lighting from low-dynamic range (LDR) background images. In an example implementation, a method may include receiving low-dynamic range (LDR) background images of scenes, each LDR background image captured with appearance of one or more reference objects with different reflectance properties; and training a lighting estimation model based at least on the received LDR background images to predict high-dynamic range (HDR) lighting based at least on the trained model. In another example implementation, a method may include capturing a low-dynamic range (LDR) background image of a scene from an LDR video captured by a camera of the electronic computing device; predicting high-dynamic range (HDR) lighting for the image, the predicting, using a trained model, based at least on the LDR background image; and rendering a virtual object based at least on the predicted HDR lighting.

Abstract: Apparatus and methods related to applying lighting models to images are provided. An example method includes receiving, via a computing device, an image comprising a subject. The method further includes relighting, via a neural network, a foreground of the image to maintain a consistent lighting of the foreground with a target illumination. The relighting is based on a per-pixel light representation indicative of a surface geometry of the foreground. The light representation includes a specular component, and a diffuse component, of surface reflection. The method additionally includes predicting, via the neural network, an output image comprising the subject in the relit foreground. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: Example embodiments relate to techniques for volumetric performance capture with neural rendering. A technique may involve initially obtaining images that depict a subject from multiple viewpoints and under various lighting conditions using a light stage and depth data corresponding to the subject using infrared cameras. A neural network may extract features of the subject from the images based on the depth data and map the features into a texture space (e.g., the UV texture space). A neural renderer can be used to generate an output image depicting the subject from a target view such that illumination of the subject in the output image aligns with the target view. The neural render may resample the features of the subject from the texture space to an image space to generate the output image.

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.

Abstract: Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.

Abstract: Systems, methods, and computer program products are described that implement obtaining, at an electronic computing device and for at least one image of a scene rendered in an Augmented Reality (AR) environment, a scene lighting estimation captured at a first time period. The scene lighting estimation may include at least a first image measurement associated with the scene. The implementations may include determining, at the electronic computing device, a second image measurement associated with the scene at a second time period, determining a function of the first image measurement and the second image measurement. Based on the determined function, the implementations may also include triggering calculation of a partial lighting estimation update or triggering calculation of a full lighting estimation update and rendering, on a screen of the electronic computing device and for the scene, the scene using the partial lighting estimation update or the full lighting estimation update.

Abstract: Techniques of estimating lighting from portraits includes generating a lighting estimate from a single image of a face based on a machine learning (ML) system using multiple bidirectional reflection distribution functions (BRDFs) as a loss function. In some implementations, the ML system is trained using images of faces formed with HDR illumination computed from LDR imagery. The technical solution includes training a lighting estimation model in a supervised manner using a dataset of portraits and their corresponding ground truth illumination.

Abstract: An example method, apparatus, and computer-readable storage medium are provided to predict high-dynamic range (HDR) lighting from low-dynamic range (LDR) background images. In an example implementation, a method may include receiving low-dynamic range (LDR) background images of scenes, each LDR background image captured with appearance of one or more reference objects with different reflectance properties; and training a lighting estimation model based at least on the received LDR background images to predict high-dynamic range (HDR) lighting based at least on the trained model. In another example implementation, a method may include capturing a low-dynamic range (LDR) background image of a scene from an LDR video captured by a camera of the electronic computing device; predicting high-dynamic range (HDR) lighting for the image, the predicting, using a trained model, based at least on the LDR background image; and rendering a virtual object based at least on the predicted HDR lighting.

Abstract: Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.

Abstract: Systems, methods, and computer program products are described that implement obtaining, at an electronic computing device and for at least one image of a scene rendered in an Augmented Reality (AR) environment, a scene lighting estimation captured at a first time period. The scene lighting estimation may include at least a first image measurement associated with the scene. The implementations may include determining, at the electronic computing device, a second image measurement associated with the scene at a second time period, determining a function of the first image measurement and the second image measurement. Based on the determined function, the implementations may also include triggering calculation of a partial lighting estimation update or triggering calculation of a full lighting estimation update and rendering, on a screen of the electronic computing device and for the scene, the scene using the partial lighting estimation update or the full lighting estimation update.

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided.