Conference on Computer Vision and Pattern Recognition (CVPR 2021)
Authors Erik Franz, Barbara Solenthaler, Nils Thuerey
Abstract
We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation. Instead of obtaining the space-time function of the observations, we reconstruct its motion based on a single initial state. In addition, we introduce a learned self-supervision that constrains observations from unseen angles. These visual constraints are coupled via the transport constraints and a differentiable rendering step to arrive at a robust end-to-end reconstruction algorithm. This makes the reconstruction of highly realistic flow motions possible, even from only a single input view. We show with a variety of synthetic and real flows that the proposed global reconstruction of the transport process yields an improved reconstruction of the fluid motion.
Links
Preprint Code Supplemental Video Supplemental Video (YouTube)
Fig. 1: Overview: We propose a novel algorithm that reconstructs the motion of a single initial state over the full course of an input sequence, i.e., its global transport. Based on a learned self-supervision, our algorithm yields a realistic motion for highly under-constrained scenarios such as a single input view.
Supplemental video. YouTube version.
Fig. 2: Example reconstruction using one of the ScalarFlow captures.