VIAFormer：用于高保真体素细化的体素-图像对齐 Transformer
VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement
把标定多视图图像作为条件来修复不完整噪声体素，其 Image Index 为 2D 图像 token 注入显式 3D 空间定位、Correctional Flow 直接学习体素细化轨迹，可作为视觉基础模型输出（如单目/多视图重建体素）的后处理精修模块复用。
原文依据 repairing incomplete noisy voxels using calibrated multi-view images as guidance
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 VIAFormer，一种面向多视图条件体素细化的体素-图像对齐 Transformer 模型，其任务是以标定多视图图像为引导，修复不完整且含噪的体素。该模型的有效性源于协同设计：图像索引为 2D 图像 token 提供显式的三维空间定位，校正流目标学习直接的体素细化轨迹，混合流 Transformer 实现稳健的跨模态融合。实验表明，无论是对强视觉基础模型所得体素形状上的严重合成损坏，还是真实伪影，VIAFormer 在修正效果上均达到新的最优水平。除基准评测之外，我们还展示了 VIAFormer 可作为真实三维创作流程中实用且可靠的桥梁，为基于体素的方法在大模型、大数据浪潮中蓬勃发展铺平道路。
英文原文摘要 899 字符
We propose VIAFormer, a Voxel-Image Alignment transFormer model designed for Multi-view Conditioned Voxel Refinement--the task of repairing incomplete noisy voxels using calibrated multi-view images as guidance. Its effectiveness stems from a synergistic design: an Image Index that provides explicit 3D spatial grounding for 2D image tokens, a Correctional Flow objective that learns a direct voxel-refinement trajectory, and a Hybrid Stream Transformer that enables robust cross-modal fusion. Experiments show that VIAFormer establishes a new state of the art in correcting both severe synthetic corruptions and realistic artifacts on the voxel shape obtained from powerful Vision Foundation Models. Beyond benchmarking, we demonstrate VIAFormer as a practical and reliable bridge in real-world 3D creation pipelines, paving the way for voxel-based methods to thrive in large-model, big-data wave.