Spatially-Grounded Flow Matching: Structured Source Distributions for Image Generation

• URL: http://arxiv.org/abs/2608.15452v1
• Date: Sun, 16 Aug 2026 00:03:21 GMT
• Title: Spatially-Grounded Flow Matching: Structured Source Distributions for Image Generation
• Abstract summary: Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images.<n>Images are fundamentally local since nearby pixels are strongly correlated.<n>We propose StructFlow which encodes spatial locality directly into the source by having the pixels within a small region share a common noise component.
• Score: 3.3692935883125954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distribution carries no notion of spatial structure. Images however are fundamentally local since nearby pixels are strongly correlated. By sampling the noise independently, we hypothesize that models are implicitly encouraged to exploit less noisy neighbors as context during training, partially bypassing the need to properly learn the true local structure of images. The source distribution, in other words, works against the inductive bias of the image domain. To ameliorate this design discrepancy, we propose StructFlow which encodes spatial locality directly into the source by having the pixels within a small region share a common noise component. This structured source produces transport paths that are geometrically aligned with image regions - enabling properties that generic flow matching struggles to provide: fine-grained local editing that naturally respects boundaries, robust structure preservation, and smooth semantic interpolation between images. We show that these benefits also extend to large pre-trained models, demonstrating that StructFlow can even be incorporated through a lightweight post-training phase. Comprehensive experiments on multiple datasets, in unconditional, class and text-conditioned regimes, using different diffusion transformer architectures confirm that StructFlow not only offers competitive image generation quality, but also significantly improves localized controllable re-synthesis.

Related papers

• StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation [72.84181869780627]
  StructDiff is a generative framework based on a single-scale diffusion model for single-image generation.<n>It incorporates 3D positional encoding (PE) as a spatial prior, allowing flexible control over positions, scale, and local details of generated objects.<n>It also demonstrates broad applicability across downstream tasks, such as text-guided image generation, image editing, outpainting, and paint-to-image synthesis.
  arXiv  Detail & Related papers  (2026-04-14T10:55:43Z)
• SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation [9.212970624261272]
  State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts.<n>We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt.<n>Our method explicitly models the signal component during the denoising process, offering fine-grained control that mitigates over-optimization.
  arXiv  Detail & Related papers  (2025-08-19T14:31:15Z)
• DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering [46.94209097951204]
  We present DNF-Intrinsic, a robust yet efficient inverse rendering approach fine-tuned from pre-trained diffusion model.<n>We show that our method clearly outperforms existing state-of-the-art rendering methods.
  arXiv  Detail & Related papers  (2025-07-05T07:11:58Z)
• Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution [14.57591222028278]
  We present a general and simple framework, CrossFlow, for cross-modal flow matching.<n>We show the importance of applying Variationals to the input data, and introduce a method to enable-free guidance.<n>To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intramodal mapping tasks.
  arXiv  Detail & Related papers  (2024-12-19T18:59:56Z)
• Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold [69.33930972652594]
  Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Existing GAN compression methods mainly rely on knowledge distillation or convolutional classifiers' pruning techniques. We propose a new approach by explicitly encouraging the pruned model to preserve the density structure of the original parameter-heavy model on its learned manifold. Our experiments on image translation GAN models, Pix2Pix and CycleGAN, with various benchmark datasets and architectures demonstrate our method's effectiveness.
  arXiv  Detail & Related papers  (2023-12-22T15:43:12Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• A Structure-Guided Diffusion Model for Large-Hole Image Completion [85.61681358977266]
  We develop a structure-guided diffusion model to fill large holes in images. Our method achieves a superior or comparable visual quality compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-18T18:59:01Z)
• Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
  In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
  arXiv  Detail & Related papers  (2021-09-13T12:45:08Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.