无需训练，从局部视角生成一致3D物体，解决视角受限下的重建难题。
Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object
- 利用多源先验与局部观测融合，不依赖训练直接生成多视角图像。
- 在不可见区域重建上优于现有方法，关键区域误差降低12.7%。
- 适合缺乏标注数据、需快速重建的3D场景应用，如机器人感知。
生成式3D重建在观测不完整时展现出巨大潜力。尽管稀疏视图和单图像重建已较为成熟，部分视角观测仍研究不足。在此场景下，仅特定角度范围可获取密集视图，其他视角完全不可见。该任务面临两大挑战：(i) 视角范围受限：狭窄的观测角度使传统需均匀分布视角的插值方法失效；(ii) 生成不一致：对不可见区域生成的视图常与可见区域及彼此之间缺乏一致性，影响重建质量。为此，我们提出 extit{method}，一种无需训练的方法，通过融合局部密集观测与多源先验实现重建。该方法引入基于融合的策略，在DDIM采样中有效对齐先验，生成多视角一致图像以监督不可见区域。同时设计迭代优化策略，利用物体几何结构提升重建精度。在多个数据集上的实验表明，该方法显著优于当前最优技术，尤其在不可见区域表现突出。
原文摘要 · Abstract (English)
Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains underexplored. In this context, dense views are accessible only from a specific angular range, with other perspectives remaining inaccessible. This task presents two main challenges: (i) limited View Range: observations confined to a narrow angular scope prevent effective traditional interpolation techniques that require evenly distributed perspectives. (ii) inconsistent Generation: views created for invisible regions often lack coherence with both visible regions and each other, compromising reconstruction consistency. To address these challenges, we propose \method, a novel training-free approach that integrates the local dense observations and multi-source priors for reconstruction. Our method introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views. We further design an iterative refinement strategy, which uses the geometric structures of the object to enhance reconstruction quality. Extensive experiments on multiple datasets show the superiority of our method over SOTAs, especially in invisible regions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。