I-Scene：三维实例模型是隐式可泛化的空间学习者
I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners
将预训练 3D 实例生成器重编程为场景级空间学习者，用模型中心的空间监督替代数据集监督，并以视角为中心的表示实现前馈式可泛化 3D 场景生成，为交互式 3D 场景理解与生成提供新范式。
原文依据 reprogram a pre-trained 3D instance generator to act as a scene-level learner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论泛化仍然是交互式三维场景生成的核心挑战。现有的基于学习的方法将空间理解建立在有限的场景数据集上，限制了对新布局的泛化。我们转而重编程一个预训练的三维实例生成器，使其通过以模型为中心的空间监督替代受数据集限制的监督，从而充当场景级学习器。这种重编程释放了生成器可迁移的空间知识，使其能够泛化到未见过的布局和新颖的物体组合。值得注意的是，即使训练场景由随机组合的物体构成，空间推理仍然涌现。这表明生成器可迁移的场景先验为从纯几何线索推断邻近性、支撑关系和对称性提供了丰富的学习信号。我们替换了广泛使用的规范空间，以视角为中心的公式化场景空间来实例化这一洞见，产生了一个完全前馈、可泛化的场景生成器，它直接从实例模型中学习空间关系。定量和定性结果表明，三维实例生成器是一个隐式的空间学习器和推理器，指向了用于交互式三维场景理解和生成的基础模型。代码可在 \href https://luling06.github.io/I-Scene-project/ 项目页面获取。
英文原文摘要 1354 字符
Generalization remains the central challenge for interactive 3D scene generation. Existing learning-based approaches ground spatial understanding in limited scene dataset, restricting generalization to new layouts. We instead reprogram a pre-trained 3D instance generator to act as a scene-level learner via, replacing dataset-bounded supervision with model-centric spatial supervision. This reprogramming unlocks the generator's transferable spatial knowledge, enabling generalization to unseen layouts and novel object compositions. Remarkably, spatial reasoning still emerges even when the training scenes are randomly composed objects. This demonstrates that the generator's transferable scene prior provides a rich learning signal for inferring proximity, support, and symmetry from purely geometric cues. Replacing widely used canonical space, we instantiate this insight with a view-centric formulation of the scene space, yielding a fully feed-forward, generalizable scene generator that learns spatial relations directly from the instance model. Quantitative and qualitative results show that a 3D instance generator is an implicit spatial learner and reasoner, pointing toward foundation models for interactive 3D scene understanding and generation. The code is accessible at \href https://luling06.github.io/I-Scene-project/ the project page .