用普通照片和少量显微镜图像，生成超大分辨率的微观纹理图。
MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale
- 分两阶段生成：先保证整体结构一致，再细化局部细节。
- 在350倍放大下实现百万级像素级图像，保持材料真实感。
- 适合需要微观可视化的大规模图像分析场景。
我们提出MicroZoom，一种用于微观尺度下十亿像素图像合成的生成框架。给定一张普通照片和少量消费级显微镜近景图像，MicroZoom可生成与真实参考材料特性一致、无缝衔接的十亿像素级图像，支持对物体全范围微观纹理的探索性可视化。目标是合理合成而非精确重建。重点解决高达350倍放大下的全图、参考驱动、极端尺度超分辨问题，面临两大挑战：(1) 在信息高度损失、材料边界模糊区域恢复特定纹理细节；(2) 在数百万局部预测中保持大尺度模式结构（如织物编织重复几何）的一致性。为此采用两级级联设计：第一阶段恢复全局图案连贯性，第二阶段精炼局部纹理细节，并辅以分割掩码指导模糊边界的合成。我们在自采集的日常物体数据集上验证方法，展示出全局连贯、材料真实的十亿像素级图像。
原文摘要 · Abstract (English)
We introduce MicroZoom, a generative framework for gigapixel image synthesis at the microscopic scale. Given a standard photograph and a sparse set of consumer-grade microscope close-ups, MicroZoom synthesizes a seamless, gigapixel-resolution image grounded in the material character of the real references, enabling exploratory visualization of microscopic texture across the full spatial extent of an object. Our goal is plausible synthesis, not exact reconstruction. We focus on full-image, reference-based, extreme-scale super-resolution at magnification levels of up to 350x, a setting that introduces two major challenges: (1) recovering texture-specific detail from highly lossy inputs near ambiguous material boundaries, and (2) preserving correct large-scale pattern structure, such as the repeating geometry of a fabric weave, across millions of local predictions. We address these with a two-stage cascaded design, where the first stage recovers global pattern coherence and the second refines local texture detail, supplemented by a segmentation mask to guide synthesis at ambiguous boundaries. We verify our approach on a collection of self-captured everyday objects and demonstrate globally coherent, materially grounded gigapixel imagery.
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。