PixARMesh：自回归网格原生的单视图场景重建
PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
把网格生成模型与像素对齐的图像特征、全局场景上下文通过交叉注意力结合，并用统一的词元流（上下文+位姿+网格）自回归地一次性输出布局与几何，为单图三维重建提供了一条绕开隐式 SDF 与后处理布局优化的端到端路线。
原文依据 augment a point-cloud encoder with pixel-aligned image features and global scene context via cross-attention
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 PixARMesh，一种直接从单张 RGB 图像自回归地重建完整三维室内场景网格的方法。与依赖隐式符号距离场和事后布局优化的先前方法不同，PixARMesh 在统一模型中联合预测物体布局与几何，单次前向传播即可生成连贯且可直接用于美术制作的网格。基于网格生成模型的最新进展，我们通过交叉注意力为点云编码器增强像素对齐的图像特征与全局场景上下文，从而能够从单张图像进行准确的空间推理。场景由包含上下文、位姿与网格的统一词元流自回归生成，得到几何保真度高的紧凑网格。在合成与真实数据集上的实验表明，PixARMesh 在达到最优重建质量的同时，还能产出轻量、高质量、可供下游应用直接使用的网格。
英文原文摘要 959 字符
We introduce PixARMesh, a method to autoregressively reconstruct complete 3D indoor scene meshes directly from a single RGB image. Unlike prior methods that rely on implicit signed distance fields and post-hoc layout optimization, PixARMesh jointly predicts object layout and geometry within a unified model, producing coherent and artist-ready meshes in a single forward pass. Building on recent advances in mesh generative models, we augment a point-cloud encoder with pixel-aligned image features and global scene context via cross-attention, enabling accurate spatial reasoning from a single image. Scenes are generated autoregressively from a unified token stream containing context, pose, and mesh, yielding compact meshes with high-fidelity geometry. Experiments on synthetic and real-world datasets show that PixARMesh achieves state-of-the-art reconstruction quality while producing lightweight, high-quality meshes ready for downstream applications.