Trajectory Stitching for Solving Inverse Problems with Flow-Based Models

arXiv:2602.08538 · eess.IV, cs.LG · Submitted 2026-02-09 · Read on arXiv

eess.IV, cs.LG

Submitted: 2026-02-09

Updated: 2026-10-01

Code: https://github.com/alexdenker/MS-Flow

Terminology

• Inverse Problem — 4× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes

Sources

• Training Deep Nets with Sublinear Memory Cost
• Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
• Classifier-Free Diffusion Guidance
• Auto-Encoding Variational Bayes
• Rectified Flow: A Marginal Preserving Approach to Optimal Transport
• Improving and generalizing flow-based generative models with minibatch optimal transport
• Training Free Guided Flow Matching with Optimal Control

Related papers

• PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution
• Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
• VesselSDF: Distance Field Priors for Vascular Network Reconstruction
• cSVR: Convolutional Slice-to-Volume Reconstruction
• NAIMA: Semantics Aware RGB Guided Depth Super-Resolution
• AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD