Abstract: In one embodiment, a method includes initializing latent codes respectively associated with times associated with frames in a training video of a scene captured by a camera. For each of the frames, a system (1) generates rendered pixel values for a set of pixels in the frame by querying NeRF using the latent code associated with the frame, a camera viewpoint associated with the frame, and ray directions associated with the set of pixels, and (2) updates the latent code associated with the frame and the NeRF based on comparisons between the rendered pixel values and original pixel values for the set of pixels. Once trained, the system renders output frames for an output video of the scene, wherein each output frame is rendered by querying the updated NeRF using one of the updated latent codes corresponding to a desired time associated with the output frame.

Abstract: In one example, an apparatus comprises a pixel cell array and a controller formed within a semiconductor package. The pixel cell array is configured to: generate, at a first time and based on first programming signals received from the controller, a first image frame; transmit the first image frame to a host processor; and transmit the first image frame or a second image frame to the controller, the second image frame being generated at the first time and having a different sparsity of pixels from the first image frame. The controller is configured to receive second programming signals from a host processor, the second programming signals being determined by the host processor based on the first image frame; update the first programming signals based on the second programming signals; and control the pixel cell array to generate a subsequent image frame based on the updated first programming signals.

Abstract: In one embodiment, a method includes determining a viewing direction of a scene and rendering an image of the scene for the viewing direction, wherein the rendering comprises: for each pixel of the image, casting a view ray into the scene, and for a particular sampling point along the view ray, determining a pixel radiance associated with surface light field (SLF) and opacity, which comprises identifying multiple voxels within a threshold distance to the particular sampling point, wherein each of the voxels is associated with a respective local plane, for each the voxels computing a pixel radiance associated with SLF and opacity based on locations of the particular sampling point and the local plane associated with that voxel, and determining the pixel radiance associated with SLF and opacity for the particular sampling point based on interpolating the pixel radiances associated with SLF and opacity associated with the multiple voxels.

Abstract: In one embodiment, a method includes initializing latent codes respectively associated with times associated with frames in a training video of a scene captured by a camera. For each of the frames, a system (1) generates rendered pixel values for a set of pixels in the frame by querying NeRF using the latent code associated with the frame, a camera viewpoint associated with the frame, and ray directions associated with the set of pixels, and (2) updates the latent code associated with the frame and the NeRF based on comparisons between the rendered pixel values and original pixel values for the set of pixels. Once trained, the system renders output frames for an output video of the scene, wherein each output frame is rendered by querying the updated NeRF using one of the updated latent codes corresponding to a desired time associated with the output frame.

Abstract: In one example, an apparatus comprises a pixel cell array and a controller formed within a semiconductor package. The pixel cell array is configured to: generate, at a first time and based on first programming signals received from the controller, a first image frame; transmit the first image frame to a host processor; and transmit the first image frame or a second image frame to the controller, the second image frame being generated at the first time and having a different sparsity of pixels from the first image frame. The controller is configured to receive second programming signals from a host processor, the second programming signals being determined by the host processor based on the first image frame; update the first programming signals based on the second programming signals; and control the pixel cell array to generate a subsequent image frame based on the updated first programming signals.