By designing the prior as the low-frequency projection of data images, flow matching achieves OT-optimal identity couplings without explicit OT computation, reducing trajectory curvature over 2x and improving few-step quality.
Neuralremaster: Phase-preserving diffusion for structure-aligned generation.arXiv preprint arXiv:2512.05106, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
CHIS steers pretrained diffusion models to generate histopathology images aligned with input structural masks via frequency-domain structural initialization and wavelet-based textural modulation without any training on annotated data.
Training-free motion conditioning for latent video diffusion by direct injection of low-frequency phase from a reference video into the diffusion noise.
citing papers explorer
-
Optimal Transport Flow Matching by Design
By designing the prior as the low-frequency projection of data images, flow matching achieves OT-optimal identity couplings without explicit OT computation, reducing trajectory curvature over 2x and improving few-step quality.
-
Controllable Histopathology Image Synthesis with Training-free Structural Initialization and Textural Modulation
CHIS steers pretrained diffusion models to generate histopathology images aligned with input structural masks via frequency-domain structural initialization and wavelet-based textural modulation without any training on annotated data.
-
{\Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation
Training-free motion conditioning for latent video diffusion by direct injection of low-frequency phase from a reference video into the diffusion noise.