SONIC: Spectral Optimization of Noise for Inpainting with Consistency

• URL: http://arxiv.org/abs/2511.19985v2
• Date: Wed, 26 Nov 2025 23:07:54 GMT
• Title: SONIC: Spectral Optimization of Noise for Inpainting with Consistency
• Abstract summary: We propose a novel training-free method for inpainting with off-the-shelf text-to-image models.<n>We argue that the missing ingredient for training-free inpainting is the optimization of the initial seed noise.<n>We demonstrate the effectiveness of our method on various inpainting tasks, outperforming the state of the art.
• Score: 16.958406334948748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting, in practice, their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue that the missing ingredient for training-free inpainting is the optimization (guidance) of the initial seed noise. We propose to optimize the initial seed noise to approximately match the unmasked parts of the data - with as few as a few tens of optimization steps. We then apply conventional training-free inpainting methods on top of our optimized initial seed noise. Critically, we propose two core ideas to effectively implement this idea: (i) to avoid the costly unrolling required to relate the initial noise and the generated outcome, we perform linear approximation; and (ii) to stabilize the optimization, we optimize the initial seed noise in the spectral domain. We demonstrate the effectiveness of our method on various inpainting tasks, outperforming the state of the art. Project page: https://ubc-vision.github.io/sonic/

Related papers

• Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization [5.814544128372275]
  Oracle Noise is a zero-shot framework reframing noise as semantic-driven optimization strictly confined to a hypersphere.<n>It significantly accelerates semantic alignment and superior aesthetics without black-box models.<n>It achieves state-of-the-art performance across human preference metrics (e.g., HPSv2, ImageReward), semantic alignment (CLIP Score), and sample diversity, all within a strict 2-second optimization budget.
  arXiv  Detail & Related papers  (2026-04-26T05:32:26Z)
• It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models [80.53672733210111]
  We show that a simple noise optimization objective can mitigate mode collapse while preserving the fidelity of the base model.<n>Our experiments demonstrate that noise optimization yields superior results in terms of generation quality and variety.
  arXiv  Detail & Related papers  (2025-12-31T19:47:49Z)
• FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting [98.04041133839088]
  Text-guided image inpainting endeavors to generate new content within specified regions of images using textual prompts from users.<n>We introduce FreeInpaint, a plug-and-play tuning-free approach that directly optimize the diffusion latents on the fly during inference to improve the faithfulness of the generated images.
  arXiv  Detail & Related papers  (2025-12-24T11:06:26Z)
• TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning [53.52543819839442]
  A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds.<n>We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them.
  arXiv  Detail & Related papers  (2025-11-27T09:14:26Z)
• OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection [0.0]
  We propose a unified framework that combines distribution-aware initial noise optimization with similarity-based token pruning.<n>Experiments on benchmark datasets, including Animal-Animal, demonstrate that OptiPrune achieves state-of-the-art prompt-image consistency with significantly reduced computational cost.
  arXiv  Detail & Related papers  (2025-07-01T14:24:40Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• Efficient Distributed Optimization under Heavy-Tailed Noise [32.96984712007111]
  TailOPT is designed to address heavy-tailed noise with potentially gradient variance and local updates.<n>$Bi2Clip$ performs coordinate-wise clipping at both the inner and outers, achieving adaptive-like performance.<n>$Bi2Clip$ demonstrates superior performance on several language tasks and models, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-02-06T15:47:18Z)
• Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction [14.93489065234423]
  We formulate the optimization as a bilevel problem.<n>We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging.
  arXiv  Detail & Related papers  (2024-12-17T16:34:32Z)
• Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity [59.75300530380427]
  We consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries. We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
  arXiv  Detail & Related papers  (2024-06-28T02:56:22Z)
• InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization [27.508861002013358]
  InitNO is a paradigm that refines the initial noise in semantically-faithful images. A strategically crafted noise optimization pipeline is developed to guide the initial noise towards valid regions. Our method, validated through rigorous experimentation, shows a commendable proficiency in generating images in strict accordance with text prompts.
  arXiv  Detail & Related papers  (2024-04-06T14:56:59Z)
• Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising [14.486289176696438]
  We propose a score priors-guided deep variational inference, namely ScoreDVI, for practical real-world denoising. We exploit a Non-$i.i.d$ Gaussian mixture model and variational noise posterior to model the real-world noise. Our method outperforms other single image-based real-world denoising methods and achieves comparable performance to dataset-based unsupervised methods.
  arXiv  Detail & Related papers  (2023-08-09T03:26:58Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• Joint inference and input optimization in equilibrium networks [68.63726855991052]
  deep equilibrium model is a class of models that foregoes traditional network depth and instead computes the output of a network by finding the fixed point of a single nonlinear layer. We show that there is a natural synergy between these two settings. We demonstrate this strategy on various tasks such as training generative models while optimizing over latent codes, training models for inverse problems like denoising and inpainting, adversarial training and gradient based meta-learning.
  arXiv  Detail & Related papers  (2021-11-25T19:59:33Z)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)

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.