Pixel-Space Diffusion via Observation Operators

• URL: http://arxiv.org/abs/2608.21885v2
• Date: Tue, 25 Aug 2026 07:30:46 GMT
• Title: Pixel-Space Diffusion via Observation Operators
• Abstract summary: We propose a unified framework that aligns full-image supervision and feature refinement with the intrinsic recovery order of image structures.<n>Experiments show that the proposed approach converges substantially faster while consistently improving generation quality, achieving an FID of 1.52 on ImageNet-256.
• Score: 22.391778551506345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pixel-space diffusion models directly model image distributions but remain difficult to optimize. Recent methods alleviate this challenge through target reparameterization, while still relying on a fixed clean-image target throughout denoising. Through empirical analysis, we identify a scale-time mismatch: image structures become predictable from coarse to fine as noise decreases, whereas existing models are forced to predict the full image even under high noise, resulting in low-SNR gradients that hinder optimization. To resolve this mismatch, we propose Observation Operator Diffusion, a unified framework that aligns both the supervision trajectory and feature refinement with the intrinsic recovery order of image structures. Specifically, we replace fixed full-image supervision along the standard flow path with a time-indexed observation trajectory that evolves from coarse structures to the full image during denoising. This trajectory is instantiated with a family of Gaussian-Lanczos operators at varying observation scales, yielding a path-consistent training objective. We further introduce GL-CoDA, a decoder that injects scale-specific Gaussian-Lanczos observations across decoding stages for coarse-to-fine feature refinement. Extensive experiments show that the proposed approach converges substantially faster while consistently improving generation quality, achieving an FID of 1.52 on ImageNet-256.

Related papers

• CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction [3.7567584936415166]
  Sparse-view computed tomography (CT) reduces radiation dose by acquiring fewer projection views, but the resulting inverse problem is highly ill-posed.<n>Existing deep reconstruction methods have achieved promising performance, yet many rely on first-order updates or large regularization networks.<n>We propose textbfCG-GLORE, a compact deep unrolling framework inspired by second-order optimization for sparse-view CT reconstruction.
  arXiv  Detail & Related papers  (2026-08-15T14:08:44Z)
• LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling [10.887547857646942]
  Distilled diffusion models accelerate image generation by reducing the number of denoising steps, but often suffer from degraded image quality.<n>Recent hypernetwork-based approaches amortize this process during training, but still require costly noise modulation in high-dimensional latent spaces.<n>We propose LENS (Low-frequency Eigen Noise Shaping), an efficient noise modulation framework that operates in a low-dimensional subspace.
  arXiv  Detail & Related papers  (2026-05-08T05:22:24Z)
• LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction [4.609499769793957]
  Diffusion-based image super-resolution (SR) aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations.<n>The state-of-the-art residual-shifting diffusion framework efficient 4-step inference suffers from severe degradation performance in compact sampling trajectories.<n>We propose a prior-enhanced efficient diffusion framework to address these issues.
  arXiv  Detail & Related papers  (2026-03-22T03:52:38Z)
• Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution [75.3690742776891]
  We propose Iterative Diffusion Inference-Time Scaling with Adaptive Frequency Steering (IAFS)<n>IAFS addresses the challenge of balancing perceptual quality and structural fidelity by progressively refining the generated image through iterative correction of structural deviations.<n>Experiments show that IAFS effectively resolves the perception-fidelity conflict, yielding consistently improved perceptual detail and structural accuracy, and outperforming existing inference-time scaling methods.
  arXiv  Detail & Related papers  (2025-12-29T15:09:20Z)
• How Noise Benefits AI-generated Image Detection [15.496270003630451]
  Out-of-distribution generalization of AI-generated images is a persistent challenge.<n>We propose the Positive-Incentive Noise for CLIP (PiN-CLIP), which jointly trains a noise generator and a detection network under a variational positive-incentive principle.<n>Our method achieves new state-of-the-art performance, with notable improvements of 5.4 in average accuracy over existing approaches.
  arXiv  Detail & Related papers  (2025-11-20T08:16:24Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising [16.43285056788183]
  We propose a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG) Our method leverages a reconstructive denoising network to recover the majority of the underlying clean signal. It employs a diffusion algorithm to generate residual high-frequency details, thereby enhancing visual quality.
  arXiv  Detail & Related papers  (2023-09-19T16:01:20Z)
• Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
  Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast. These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. We first propose a method for estimating the noise level in low light images in a quick and accurate way. We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
  arXiv  Detail & Related papers  (2023-05-17T13:56:48Z)
• On Measuring and Controlling the Spectral Bias of the Deep Image Prior [63.88575598930554]
  The deep image prior has demonstrated the remarkable ability that untrained networks can address inverse imaging problems. It requires an oracle to determine when to stop the optimization as the performance degrades after reaching a peak. We study the deep image prior from a spectral bias perspective to address these problems.
  arXiv  Detail & Related papers  (2021-07-02T15:10:42Z)
• Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
  We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
  arXiv  Detail & Related papers  (2020-12-18T08:25:39Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.