Global Transport for Fluid Reconstruction with Learned Self-Supervision

2021/04/13 by Erik Franz, Franz, Aleksandra, Barbara Solenthaler +3 · 3 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn)

paper · pdf · doi:10.48550/arxiv.2104.06031

openalex publication_date 2021/04/13 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

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.

Cited by

• FlowCapX: Physics-Grounded Flow Capture with Long-Term Consistency
• Learning an Implicit Physics Model for Image-based Fluid Simulation
• SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models

Related

• Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision
• Coupled Fluid Density and Motion from Single Views
• Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion
• Operator Learning for Reconstructing Flow Fields from Sparse Measurements: an Energy Transformer Approach
• Inferring Fluid Dynamics via Inverse Rendering