NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
Abstract
Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial structure, making it ill-suited for tasks requiring geometric consistency, such as re-rendering, simulation enhancement, and image-to-image translation. We introduce Phase-Preserving Diffusion (\phi-PD), a model-agnostic reformulation of the diffusion process that preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes or additional parameters. We further propose Frequency-Selective Structured (FSS) noise, which provides continuous control over structural rigidity via a single frequency-cutoff parameter. \phi-PD adds no inference-time cost and is compatible with any diffusion model for images or videos. Across photorealistic and stylized re-rendering, as well as sim-to-real enhancement for driving planners, \phi-PD produces controllable, spatially aligned results. When applied to the CARLA simulator, \phi-PD significantly improves sim-to-real planner transfer performance. The method is complementary to existing conditioning approaches and broadly applicable to image-to-image and video-to-video generation. Videos, additional examples, and code are available on our \href{https://yuzeng-at-tri.github.io/ppd-page/}{project page}.
Cite
@article{arxiv.2512.05106,
title = {NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation},
author = {Yu Zeng and Charles Ochoa and Mingyuan Zhou and Vishal M. Patel and Vitor Guizilini and Rowan McAllister},
journal= {arXiv preprint arXiv:2512.05106},
year = {2026}
}