Coarse3D：可控制朝向且忠实还原输入图像的稀疏结构生成模型
Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D
一篇 arXiv 论文，提出 Coarse3D，解决图生 3D 粗阶段朝向不受控、和输入图对不上的老毛病，能直接插进现有管线用。
Coarse3D 是一个从无位姿图像生成稀疏体素结构的 3D 生成模型，针对现有粗阶段生成器朝向难控制、结构与输入图像不一致两大问题提出三项设计：首帧锚定规范化空间、双塔 DiT 结合前馈重建学习空间接地特征、以及基于像素到体素对应的空间先验引导注意力。该模型可直接替换现有 from 粗到细 3D 生成管线的粗阶段。实验显示它在稀疏结构质量上显著提升，并稳定改善最终 3D 生成效果，达到 state-of-the-art 性能。
Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D
Coarse-to-fine 3D-native generation relies heavily on the first-stage sparse structure, which determines the global orientation and overall geometry for subsequent refinement. However, existing coarse generators suffer from two key limitations: their orientation is difficult to control due to ambiguous semantic canonicalization, and their structures are often inconsistent with input images due to weak 2D-3D grounding. We propose Coarse3D, a sparse-structure generation model that produces orientation-controllable and structurally faithful voxel geometry from arbitrary unposed images. Coarse3D introduces three designs: a first-frame anchored canonical space that aligns generation with the first input view while preserving object-centric normalization; a dual-tower DiT that couples generation with auxiliary feed-forward reconstruction to learn spatially grounded features; and spatial-prior guided attention that regularizes cross-attention with pixel-to-voxel correspondence. Coarse3D can directly replace the coarse stage of existing pipelines. Experiments show that it substantially improves sparse structure quality and consistently enhances final 3D generation, achieving state-of-the-art performance.