让模糊人脸根据文字提示生成多种合理修复结果。
Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration
- 通过测量约束构建逆问题，实现文本引导的采样
- 在多个提示下生成与输入结构一致的多样修复结果
- 适合需要多方案输出的模糊人脸修复场景
极端低质量输入下的盲人脸修复（BFR）可能对应多个合理的高质量重建。现有方法通常产生确定性结果，难以捕捉这种一因多果的特性。本文提出测量约束采样（MCS）方法，实现基于不同文本提示的多样化低质量人脸重建。具体地，通过控制粗略修复结果的退化过程，将BFR建模为测量约束的生成任务，支持在文生图扩散模型中进行后验引导采样。测量约束包括正向测量（确保结果与输入结构一致）和反向测量（生成投影空间，使解能匹配多种提示）。实验表明，MCS可生成与提示对齐的结果，且优于现有BFR方法。代码将在论文接受后发布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。