Search

Volumetric phenomena, such as clouds and fog, present a significant challenge for 3D reconstruction systems due to their translucent nature and their complex interactions with light. Conventional techniques for reconstructing scattering volumes rely on controlled setups, limiting practical applications. This paper introduces an approach to reconstructing volumes from a few input stereo pairs. We propose a novel deep learning framework that integrates a deep stereo model with a 3D Convolutional Neural Network (3D CNN) and an advection module, capable of capturing the shape and dynamics of volumes. The stereo depths are used to carve empty space around volumes, providing the 3D CNN with a prior for coping with the lack of input views. Refining our output, the advection module leverages the temporal evolution of the medium, providing a mechanism to infer motion and improve temporal consistency. The efficacy of our system is demonstrated through its ability to estimate density and velocity fields of large-scale volumes, in this case, clouds, from a sparse set of stereo image pairs., Comment: Project page at https://cloud-field.github.io

This is one in a series of SMSG supplementary and enrichment pamphlets for high school students. This series is designed to make material for the study of topics of special interest to students readily accessible in classroom quantity. Topics covered include the law of decay, relative rate of change, and a general solution. (MP)

This is one in a series of manuals for teachers using SMSG high school supplementary materials. The pamphlet includes commentaries on the sections of the student's booklet, answers to the exercises, and sample test questions. Topics covered include points, lines, space, planes, names, intersection of sets, intersection of lines and planes, segments, separations, angles, one-to-one correspondence, and simple closed curves. (MP)

This is one in a series of SMSG supplementary and enrichment pamphlets for high school students. This series is designed to make material for the study of topics of special interest to students readily accessible in classroom quantity. Topics covered include points, lines, space, planes, segments, separations, angles, one-to-one correspondence, and simple closed curves. (MP)