Abstract: Methods and systems for scene reconstruction are disclosed. The methods and systems include: receiving a set of frames for a scene, group the set of frames into multiple groups, merging multiple first and second frames in first and second initial groups of the multiple groups to generate first and merged frames, respectively, determining a homography across the first and second merged frames, and interpolating the homography to generate a warp to warp the set of frames. Then, the methods and system can repeat the grouping, the merging, the homography determining, and the interpolation. Then, the methods and system can provide a reconstructed image based on the warp of the set of frames. Other aspects, embodiments, and features are also claimed and described.

Abstract: In accordance with some embodiments, systems, methods, and media for estimating a depth and orientation of a portion of a scene using a single-photon detector and diffuse light source are provided. In some embodiments, a system comprises: a light source; an image sensor comprising a pixel having a field of view of at least one degree; a hardware processor programmed to: cause the light source to emit a sequence of n defocused pulses toward the scene; receive, from the pixel, information indicative of arrival times of light from the scene; generate a transient histogram using the information indicative of arrival times of light from the scene; and estimate one or more properties of a portion of the scene within the field of view of the pixel based on the transient histogram, wherein the one or more properties of the portion of the scene includes at least a depth.