PG-ControlNet: A Physics-Guided ControlNet for Generative Spatially Varying Image Deblurring

• URL: http://arxiv.org/abs/2511.21043v1
• Date: Wed, 26 Nov 2025 04:19:51 GMT
• Title: PG-ControlNet: A Physics-Guided ControlNet for Generative Spatially Varying Image Deblurring
• Authors: Hakki Motorcu, Mujdat Cetin,
• Abstract summary: We propose a novel framework to tame spatially varying image deblurring.<n>Rather than oversimplifying the degradation field, we model it as a dense continuum of high-dimensional compressed kernels.<n>Our method effectively bridges the gap between physical accuracy and perceptual realism.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatially varying image deblurring remains a fundamentally ill-posed problem, especially when degradations arise from complex mixtures of motion and other forms of blur under significant noise. State-of-the-art learning-based approaches generally fall into two paradigms: model-based deep unrolling methods that enforce physical constraints by modeling the degradations, but often produce over-smoothed, artifact-laden textures, and generative models that achieve superior perceptual quality yet hallucinate details due to weak physical constraints. In this paper, we propose a novel framework that uniquely reconciles these paradigms by taming a powerful generative prior with explicit, dense physical constraints. Rather than oversimplifying the degradation field, we model it as a dense continuum of high-dimensional compressed kernels, ensuring that minute variations in motion and other degradation patterns are captured. We leverage this rich descriptor field to condition a ControlNet architecture, strongly guiding the diffusion sampling process. Extensive experiments demonstrate that our method effectively bridges the gap between physical accuracy and perceptual realism, outperforming state-of-the-art model-based methods as well as generative baselines in challenging, severely blurred scenarios.

Related papers

• PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models [100.65199317765608]
  Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation.<n>We introduce a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces.<n>We extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning.
  arXiv  Detail & Related papers  (2026-01-16T08:40:10Z)
• Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality [52.57416398859353]
  We show that causal minimality can endow latent representations of diffusion vision and autoregressive language models with clear causal interpretation and robust, component-wise identifiable control.<n>We introduce a novel theoretical framework for hierarchical selection models, where higher-level concepts emerge from the constrained composition of lower-level variables.<n>These causally grounded concepts serve as levers for fine-grained model steering, paving the way for transparent, reliable systems.
  arXiv  Detail & Related papers  (2025-12-11T14:59:14Z)
• Penalizing Boundary Activation for Object Completeness in Diffusion Models [35.58050562158284]
  Diffusion models have emerged as a powerful technique for text-to-image (T2I) generation.<n>In this study, we conduct an in-depth analysis of the incompleteness issue and reveal that the primary factor behind incomplete object generation is the usage of RandomCrop during model training.<n>We propose a training-free solution that penalizes activation values at image boundaries during the early denoising steps.
  arXiv  Detail & Related papers  (2025-09-21T07:58:48Z)
• VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling [68.65587507038539]
  We present a novel video diffusion-enhanced 4D Gaussian Splatting framework for dynamic urban scene modeling.<n>Our key insight is to distill robust, temporally consistent priors from a test-time adapted video diffusion model.<n>Our method significantly enhances dynamic modeling, especially for fast-moving objects, achieving an approximate PSNR gain of 2 dB.
  arXiv  Detail & Related papers  (2025-08-04T07:24:05Z)
• BokehDiff: Neural Lens Blur with One-Step Diffusion [62.59018200914645]
  We introduce BokehDiff, a lens blur rendering method that achieves physically accurate and visually appealing outcomes.<n>Our method employs a physics-inspired self-attention module that aligns with the image formation process.<n>We adapt the diffusion model to the one-step inference scheme without introducing additional noise, and achieve results of high quality and fidelity.
  arXiv  Detail & Related papers  (2025-07-24T03:23:19Z)
• RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation [10.956556608715035]
  Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts.<n>We propose a flexible training-free framework that decouples the sampling schedule of condition features from the denoising process.<n>We further enhance the sampling process by introducing a restart refinement schedule, and improve the visual quality with an appearance-rich prompting strategy.
  arXiv  Detail & Related papers  (2025-07-03T16:56:15Z)
• Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation [31.868248649812088]
  Cloth manipulation is challenging due to its highly complex dynamics, near-infinite degrees of freedom, and frequent self-occlusions.<n>We propose a diffusion-based generative approach for both perception and dynamics modeling.<n>We show that our framework enables effective cloth folding on real robotic systems.
  arXiv  Detail & Related papers  (2025-03-15T05:34:26Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• HRR: Hierarchical Retrospection Refinement for Generated Image Detection [16.958383381415445]
  We propose a diffusion model-based generative image detection framework termed Hierarchical Retrospection Refinement(HRR)<n>The HRR framework consistently delivers significant performance improvements, outperforming state-of-the-art methods in generated image detection task.
  arXiv  Detail & Related papers  (2025-02-25T05:13:44Z)
• FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference [36.02645364048733]
  We propose FFHFlow, a flow-based variational framework that generates diverse, robust multi-finger grasps.<n>By exploiting the invertibility and exact likelihoods of flows, FFHFlow introspects shape uncertainty in partial observations.<n>We also integrate a discriminative grasp evaluator with the flow likelihoods, formulating an uncertainty-aware ranking strategy.
  arXiv  Detail & Related papers  (2024-07-21T13:33:08Z)
• SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams [44.02794438687478]
  Spike cameras have proven effective in capturing motion features and beneficial for solving this ill-posed problem. Existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios. We propose the first self-supervised framework for the task of spike-guided motion deblurring.
  arXiv  Detail & Related papers  (2024-03-14T15:29:09Z)
• Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
  We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
  arXiv  Detail & Related papers  (2022-06-08T04:09:13Z)
• Image Reconstruction of Static and Dynamic Scenes through Anisoplanatic Turbulence [1.6114012813668934]
  We present a unified method for atmospheric turbulence mitigation in both static and dynamic sequences. We are able to achieve better results compared to existing methods by utilizing a novel space-time non-local averaging method.
  arXiv  Detail & Related papers  (2020-08-31T19:20:46Z)

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.