FlowFixer：面向细节保持的主体驱动生成
FlowFixer: Towards Detail-Preserving Subject-Driven Generation
把主体驱动生成拆成「粗生成 + 图像到图像精修」两段，并用一步去噪构造自监督配对数据来模拟尺度/视角变化导致的细节丢失；做个性化生成或参考图保真时可直接复用该精修框架与关键点匹配保真度指标。
原文依据 FlowFixer proposes direct image-to-image translation from visual references, avoiding ambiguities in language prompts.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 FlowFixer，一个用于主体驱动生成（SDG）的精修框架，可恢复生成过程中因主体尺度与视角变化而丢失的细节。FlowFixer 提出从视觉参考直接进行图像到图像翻译，从而避免语言提示中的歧义。为支持图像到图像训练，本文引入一步去噪方案来生成自监督训练数据，该方案在保留全局结构的同时自动去除高频细节，有效模拟真实世界中的 SDG 误差。本文进一步提出一种基于关键点匹配的指标，以恰当评估超出 CLIP 或 DINO 通常所测语义相似度的细节保真度。实验结果表明，FlowFixer 在定性与定量评估中均优于最优的 SDG 方法，为高保真主体驱动生成树立了新的基准。
英文原文摘要 919 字符
We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a subject. FlowFixer proposes direct image-to-image translation from visual references, avoiding ambiguities in language prompts. To enable image-to-image training, we introduce a one-step denoising scheme to generate self-supervised training data, which automatically removes high-frequency details while preserving global structure, effectively simulating real-world SDG errors. We further propose a keypoint matching-based metric to properly assess fidelity in details beyond semantic similarities usually measured by CLIP or DINO. Experimental results demonstrate that FlowFixer outperforms state-of-the-art SDG methods in both qualitative and quantitative evaluations, setting a new benchmark for high-fidelity subject-driven generation.