Global Transport for Fluid Reconstruction with Learned Self-Supervision
This addresses the challenge of realistic fluid motion reconstruction for computer graphics or simulation applications, representing an incremental advance in the field.
The paper tackles the problem of reconstructing volumetric fluid flows from sparse views by introducing a global transport formulation and learned self-supervision, achieving improved reconstruction of fluid motion from as few as a single input view.
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.