SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation

• URL: http://arxiv.org/abs/2607.02628v1
• Date: Thu, 02 Jul 2026 13:24:53 GMT
• Title: SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation
• Abstract summary: SE-UNet is a framework designed to solve ill-posed imaging tasks without extensive pre-training.<n>Our method surpasses Deep Image Prior (DIP) baselines by over 4 dB in PSNR.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty of imposing strict physical constraints. In this work, we introduce \textbf{SE-UNet} (Singular Equivariant UNet), a framework designed to solve ill-posed imaging tasks without extensive pre-training. By treating generation as an optimization problem constrained by geometric equivariance ($D_4$ group) and singular value gating, SE-UNet effectively standardizes the solution space. We demonstrate that these strong inductive biases allow for state-of-the-art zero-shot inpainting results (80\% missing pixels) on CIFAR-10. Our method surpasses Deep Image Prior (DIP) baselines by over 4 dB in PSNR and exhibits a characteristic "singular snap" convergence -- rapidly locking into the signal manifold. SE-UNet thus offers a data-efficient pathway for constrained generation, aligning with the ReALM-GEN goal of bridging theoretical priors with practical deployment.

Related papers

• Dehaze-GaussianImage: Zero-Shot Dehazing via Efficient 2D Gaussian Splatting Representation [25.472500911155347]
  We propose Dehaze-GaussianImage, the first zero-shot framework that introduces 2D Gaussian Splatting into the image dehazing domain.<n>Specifically, we propose a novel reconstruction-decoupling zero-shot learning strategy that embeds the atmospheric scattering model into the Gaussian parameter space.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in a fully unsupervised manner.
  arXiv  Detail & Related papers  (2026-06-15T03:25:56Z)
• Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration [36.68260793473452]
  Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training.<n>We propose a unified physical zero-shot image restoration framework that explicitly models heterogeneous degradations into a homogeneous all-in-one distribution.<n>Our method achieves state-of-the-art performance across both single and mixed degradations.
  arXiv  Detail & Related papers  (2026-05-23T14:08:23Z)
• GSNR: Graph Smooth Null-Space Representation for Inverse Problems [24.2377690980591]
  Inverse problems in imaging are ill-posed, leading to infinitely many solutions consistent with the measurements due to the nontrivial null-space of the sensing matrix.<n>We propose Graph-Smooth Null-Space Representation (GSNR), a mechanism that imposes structure only into the invisible component.
  arXiv  Detail & Related papers  (2026-02-23T20:24:00Z)
• PDE-Constrained Optimization for Neural Image Segmentation with Physics Priors [0.0]
  Images of microscopy images constitutes an ill-posed inverse problem due to measurement noise, weak object boundaries, and limited labeled data.<n>In this work, image segmentation is formulated as a PDE-constrained optimization problem that integrates physically motivated priors into deep learning models.<n>Experiments are conducted on the LIVECell dataset, a high-quality, manually annotated collection of phase-contrast microscopy images.
  arXiv  Detail & Related papers  (2026-02-01T07:28:14Z)
• Total Variation Subgradient Guided Image Fusion for Dual-Camera CASSI System [3.414706880536149]
  Spectral imaging technology has long-faced fundamental challenges in balancing spectral, spatial, and temporal resolutions.<n>Traditional model-based methods exhibit limited performance due to reliance on handcrafted inherent image priors.<n>We propose a dual-camera CASSI reconstruction framework that integrates total variation (TV) subgradient theory.
  arXiv  Detail & Related papers  (2025-09-13T16:57:06Z)
• Convex Latent-Optimized Adversarial Regularizers for Imaging Inverse Problems [8.33626757808923]
  We introduce Convex Latent-d Adrial Regularizers (CLEAR), a novel and interpretable data-driven paradigm. CLEAR represents a fusion of deep learning (DL) and variational regularization. Our method consistently outperforms conventional data-driven techniques and traditional regularization approaches.
  arXiv  Detail & Related papers  (2023-09-17T12:06:04Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models [54.1843419649895]
  A major challenge in using generative models to accomplish this task is the lack of paired data containing all modalities and corresponding outputs. We propose a solution based on a denoising diffusion probabilistic synthesis models to generate images under multi-model priors.
  arXiv  Detail & Related papers  (2022-06-10T12:23:05Z)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)
• Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
  Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
  arXiv  Detail & Related papers  (2020-08-25T03:30:53Z)
• The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
  We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
  arXiv  Detail & Related papers  (2020-05-16T08:17:44Z)

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.