Global Transport for Fluid Reconstruction with Learned Self-Supervision

TL;DR

This paper introduces a global transport-based method for reconstructing volumetric fluid flows from sparse views, leveraging learned self-supervision and differentiable rendering to achieve realistic motion reconstruction from minimal input views.

Contribution

It presents a novel end-to-end approach combining global transport formulation with learned self-supervision for fluid reconstruction from limited views.

Findings

Improved fluid motion reconstruction from sparse views.

Effective use of learned self-supervision for unseen angles.

Robust results on synthetic and real flow data.

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.