Abstract
We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation priors, existing methods struggle to simultaneously produce high-quality geometry and accurate poses under severe occlusion and open-set settings. To address these issues, we first decouple the de-occlusion model from 3D object generation, and enhance it by leveraging image datasets and collected de-occlusion datasets for much more diverse open-set occlusion patterns. Then, we propose a unified pose estimation model that integrates global and local mechanisms for both self-attention and cross-attention to improve accuracy. Besides, we construct an open-set 3D scene dataset to further extend the generalization of the pose estimation model. Comprehensive experiments demonstrate the superiority of our decoupled framework on both indoor and open-set scenes. Our codes and datasets is released at this https URL.
Abstract (translated)
在本文中，我们提出了一种称为SceneMaker的解耦3D场景生成框架。由于缺乏足够的开放集去遮挡和姿态估计先验知识，在严重遮挡和开放集设置下同时产生高质量几何形状和准确的姿态方面，现有方法面临挑战。为了解决这些问题，我们首先将去遮挡模型从三维物体生成中分离出来，并通过利用图像数据集和收集的去遮挡数据集来增强其多样性，以处理更加多样化的开放集遮挡模式。此外，我们提出了一种统一的姿态估计模型，该模型结合了全局和局部机制的自我注意和交叉注意力，以提高准确性。另外，我们构建了一个开放集3D场景数据集，进一步扩展姿态估计模型的泛化能力。全面的实验表明，在室内和开放集场景中，我们的解耦框架具有优越性。我们的代码和数据集可在[此处](https://此URL/)获取。
URL
https://arxiv.org/abs/2512.10957
