Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration

• URL: http://arxiv.org/abs/2511.14213v1
• Date: Tue, 18 Nov 2025 07:44:54 GMT
• Title: Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration
• Authors: Wenjie Li, Yulun Zhang, Guangwei Gao, Heng Guo, Zhanyu Ma,
• Abstract summary: Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs.<n>We propose a Measurement-Constrained Sampling (MCS) approach that enables diverse LQ face reconstructions conditioned on different textual prompts.
• Score: 60.45423400845294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs. However, existing methods typically produce deterministic results, struggling to capture this one-to-many nature. In this paper, we propose a Measurement-Constrained Sampling (MCS) approach that enables diverse LQ face reconstructions conditioned on different textual prompts. Specifically, we formulate BFR as a measurement-constrained generative task by constructing an inverse problem through controlled degradations of coarse restorations, which allows posterior-guided sampling within text-to-image diffusion. Measurement constraints include both Forward Measurement, which ensures results align with input structures, and Reverse Measurement, which produces projection spaces, ensuring that the solution can align with various prompts. Experiments show that our MCS can generate prompt-aligned results and outperforms existing BFR methods. Codes will be released after acceptance.

Related papers

• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• inversedMixup: Data Augmentation via Inverting Mixed Embeddings [45.12897360336728]
  Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio.<n>InversedMixup combines the controllability of Mixup with the interpretability of LLM-based generation.
  arXiv  Detail & Related papers  (2026-01-29T11:00:50Z)
• SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples [22.912528721457473]
  In many real-world scenarios, obtaining fully observed samples is expensive or even infeasible.<n>In this work, we study distribution restoration with abundant noisy samples, assuming the corruption process is available as a black-box generator.<n>We show that this task can be framed as a one-sided optimal transport problem and solved via an EM-like algorithm.
  arXiv  Detail & Related papers  (2025-12-18T20:37:56Z)
• 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)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• Prototype Clustered Diffusion Models for Versatile Inverse Problems [11.55838697574475]
  We show that the measurement-based likelihood can be renovated with restoration-based likelihood via the opposite probabilistic graphic direction. We can resolve inverse problems with bunch of choices for assorted sample quality and realize the proficient deterioration control with assured realistic.
  arXiv  Detail & Related papers  (2024-07-13T04:24:53Z)
• BFRFormer: Transformer-based generator for Real-World Blind Face Restoration [37.77996097891398]
  We propose a Transformer-based blind face restoration method, named BFRFormer, to reconstruct images with more identity-preserved details in an end-to-end manner. Our method outperforms state-of-the-art methods on a synthetic dataset and four real-world datasets.
  arXiv  Detail & Related papers  (2024-02-29T02:31:54Z)
• Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling [26.420235903805782]
  We propose a unified end-to-end trainable inverse-like antagonistic text spotting framework dubbed IATS. Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary. We show that our method achieves superior performance both on irregular and inverse-like text spotting.
  arXiv  Detail & Related papers  (2024-01-08T02:47:47Z)
• Improving Diffusion Models for Inverse Problems using Manifold Constraints [55.91148172752894]
  We show that current solvers throw the sample path off the data manifold, and hence the error accumulates. To address this, we propose an additional correction term inspired by the manifold constraint. We show that our method is superior to the previous methods both theoretically and empirically.
  arXiv  Detail & Related papers  (2022-06-02T09:06:10Z)
• Deblurring via Stochastic Refinement [85.42730934561101]
  We present an alternative framework for blind deblurring based on conditional diffusion models. Our method is competitive in terms of distortion metrics such as PSNR.
  arXiv  Detail & Related papers  (2021-12-05T04:36:09Z)
• Adaptive Shrink-Mask for Text Detection [91.34459257409104]
  Existing real-time text detectors reconstruct text contours by shrink-masks directly. The dependence on predicted shrink-masks leads to unstable detection results. Super-pixel Window (SPW) is designed to supervise the network.
  arXiv  Detail & Related papers  (2021-11-18T07:38:57Z)
• Sampling possible reconstructions of undersampled acquisitions in MR imaging [9.75702493778194]
  Undersampling the k-space during MR saves time, however results in an ill-posed inversion problem, leading to an infinite set of images as possible solutions. Traditionally, this is tackled as a reconstruction problem by searching for a single "best" image out of this solution set according to some chosen regularization or prior. We propose a method that instead returns multiple images which are possible under the acquisition model and the chosen prior to capture the uncertainty in the inversion process.
  arXiv  Detail & Related papers  (2020-09-30T18:20:06Z)
• Conditional Sampling with Monotone GANs: from Generative Models to Likelihood-Free Inference [4.913013713982677]
  We present a novel framework for conditional sampling of probability measures, using block triangular transport maps. We develop the theoretical foundations of block triangular transport in a Banach space setting. We then introduce a computational approach, called monotone generative adversarial networks, to learn suitable block triangular maps.
  arXiv  Detail & Related papers  (2020-06-11T19:15:43Z)

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.