发表机构
Delft University of Technology（代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ElasticFit提出一种VLM引导的3D物体插入框架，通过场景基础表示推断适配提示，实现几何适配与物理合理性，显著提升空间关系和支撑成功率。
AI 中文摘要
将物体插入到现有3D场景中，需要的不仅仅是选择一个看似合理的位置：插入的物体还必须适应局部几何结构，同时保持语义意图和物理合理性。尽管最近的视觉语言模型（VLM）和生成模型能够实现语义推理和视觉内容创建，但当插入的物体必须适应受限的局部空间时，它们提供的3D基础和几何控制有限。我们引入了ElasticFit，一个以VLM为指导的框架，用于适配感知的物体插入，其核心是一种新颖的场景基础表示。给定语言指令和渲染的场景观察，ElasticFit推断出结构化的适配提示，这些提示指定了物体应在地面上的位置、应占用的体积、应如何定向以及其适配模式（刚性放置、均匀缩放或弹性适配）。这些提示将高层次的VLM推理转化为显式的3D约束，这些约束调节物体生成并指导下游的几何适配。ElasticFit随后生成一个场景条件下的物体先验，在3D中重建它，并通过特定模式的适配来细化网格，同时确保碰撞避免、接触一致性和物理基础。在固定资产基线的比较中，ElasticFit将空间关系成功率从50.8%提高到69.7%，将支撑成功率从48.3%提高到91.7%，超过了最强基线，同时为复杂场景中的生成式“使其适配”插入提供了新的支持。
英文摘要
Inserting objects into existing 3D scenes requires more than selecting a plausible location: the inserted object must also fit local geometry while preserving semantic intent and physical plausibility. Although recent Vision-Language Models (VLMs) and generative models enable semantic reasoning and visual content creation, they offer limited 3D grounding and geometric control when an inserted object must fit into constrained local spaces. We introduce ElasticFit, a VLM-guided framework for fit-aware object insertion centered on a novel scene-grounded representation. Given a language instruction and rendered scene observations, ElasticFit infers structured fitting cues that specify where the object should be grounded, what volume it should occupy, how it should be oriented, and its adaptation mode (rigid placement, uniform scaling, or elastic fitting). These cues convert high-level VLM reasoning into explicit 3D constraints that condition object generation and guide downstream geometric fitting. ElasticFit then generates a scene-conditioned object prior, reconstructs it in 3D, and refines the mesh through mode-specific fitting while enforcing collision avoidance, contact consistency, and physical grounding. In fixed-asset baseline comparisons, ElasticFit improves spatial relation success from 50.8% to 69.7% and support success from 48.3% to 91.7% over the strongest baseline, while providing novel support for generative "make-it-fit" insertions in complex scenarios.
CommentsAccepted at NeurIPS 2026. Project page: https://celine-hsieh.github.io/elasticfit/
