Coarse3D：可控且忠实的稀疏结构生成，用于图像转 3D
Coarse3D: Controllable and Faithful Sparse Structure Generation for Image-to-3D
AI 导读
Coarse3D 是一个稀疏结构生成模型，可从任意无位姿图像生成朝向可控、结构忠实的体素几何。它引入首帧锚定规范空间、双塔 DiT 以及空间先验引导注意力三项设计，并可直接替换现有流程的粗阶段。实验显示其显著提升稀疏结构质量并增强最终 3D 生成效果，达到 SOTA。
正文 · 原文
Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41231 [cs.CV] |
| (or arXiv:2610.41231v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41231 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hao Ren [view email]
[v1]
Fri, 30 Oct 2026 04:09:19 UTC (12,314 KB)
来源：arXiv cs.AI · arxiv.org