FILIGREE3D：扩展稀疏潜流匹配以实现超高分辨率图像到三维生成
FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation
- AlibabaGroup（阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Filigree3D提出稀疏潜流匹配框架，通过结构感知稀疏缩放、多尺度特征注入和可见性感知正则化，实现单图至2048^3体素分辨率的超高分辨率三维生成，显著提升几何保真度与细节保留。
AI中文摘要：
将图像到三维生成扩展到超高分辨率，需要在控制快速增长的计算成本的同时，不牺牲精细的几何细节。我们提出了Filigree3D，一个稀疏潜流匹配框架，能够从单张图像生成体素分辨率高达2048^3的三维几何体，并可轻松扩展至4096^3。为了使训练可行，我们引入了结构感知的稀疏缩放技术，该技术结合了空间边界与交替的局部-全局注意力，以限制令牌增长，同时保留细粒度细节和长距离结构上下文。为了增强细节重建，我们基于高分辨率几何增益来策划训练样本，并将多尺度图像特征注入到稀疏三维扩散Transformer中，有效耦合结构语义与细粒度视觉线索。此外，一种可见性感知的体素正则化策略提高了对稀疏扰动的鲁棒性，并促进了对未观测几何的补全。在我们的默认配置下，Filigree3D将峰值GPU内存消耗维持在当代硬件的实际限制内，使得能够在大约一分钟内生成高度复杂的三维几何体。大量实验表明，与现有基线相比，我们的方法在整体几何保真度和细节保留方面取得了显著改进，验证了在空前分辨率下进行实用且保留细节的三维生成。
英文摘要：
Scaling image-to-3D generation to ultra-high resolutions requires controlling rapidly growing computational costs without sacrificing fine geometric detail. We present \textbf{Filigree3D}, a sparse latent flow-matching framework that generates 3D geometry from a single image at voxel resolutions up to $2048^3$, with straightforward extensibility to $4096^3$. To make training tractable, we introduce Structure-Aware Sparse Scaling, which combines spatial bounding with alternating local-global attention to constrain token growth while preserving both fine-scale details and long-range structural context. To enhance detail reconstruction, we curate training samples based on their high-resolution geometric gains and inject multi-scale image features into a sparse 3D DiT, effectively coupling structural semantics with fine-grained visual cues. Furthermore, a visibility-aware voxel regularization strategy improves robustness against sparse perturbations and facilitates the completion of unobserved geometry. Under our default configuration, Filigree3D maintains peak GPU memory consumption within practical limits for contemporary hardware, enabling the generation of highly intricate 3D geometry in approximately one minute. Extensive experiments demonstrate that our method yields substantial improvements in overall geometric fidelity and fine-detail preservation compared to existing baselines, validating practical, detail-preserving 3D generation at unprecedented resolutions.
