{"ID":2833150,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05106","arxiv_id":"2512.05106","title":"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 (φ-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. φ-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, φ-PD produces controllable, spatially aligned results. When applied to the CARLA simulator, φ-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}.","short_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-ren...","url_abs":"https://arxiv.org/abs/2512.05106","url_pdf":"https://arxiv.org/pdf/2512.05106v3","authors":"[\"Yu Zeng\",\"Charles Ochoa\",\"Mingyuan Zhou\",\"Vishal M. Patel\",\"Vitor Guizilini\",\"Rowan McAllister\"]","published":"2025-12-04T18:59:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\",\"cs.LG\",\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false}