GenSplat：弥合 3DGS 语言理解中的泛化差距
GenSplat: Bridging the Generalization Gap in 3DGS Language Comprehension
把自由形式语言查询对齐到 3D 高斯表示上，用渐进式课程学习加 MLLM 语义/空间先验做 3D 定位与推理，可直接迁移到 3DGS 场景的开放词表分割、指代定位与 3D VQA 等下游任务。
原文依据 formulate a structured learning process to progressively align linguistic concepts with 3D Gaussians
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 GenSplat，一种用于三维高斯泼溅（3DGS）语言理解的新方法。已有方法要么受限于预定义词表来实现跨场景泛化，要么通过对单个场景过拟合来处理自由形式语言；与之不同，GenSplat 对自由形式语言查询具有鲁棒性，并能在不同 3DGS 场景表示之间泛化。针对该问题的核心思路是构建一个结构化的学习过程，将语言概念逐步与三维高斯对齐。该过程包含两项新颖的技术贡献。第一，我们提出渐进式语言视觉定位课程，以结构化方式引导模型从类别级语义学习到实例级概念，再到自由形式语言，从而通过构建可泛化的语言特征空间来防止过拟合。第二，我们设计了一个由多模态大语言模型（MLLM）引导的推理模块，利用 MLLM 的语义与空间先验来增强三维定位与推理。为进一步提升空间对齐与计算效率，我们引入几何感知帧选择器（GAFS），它基于高斯与纹理线索自适应地选择信息量最大的视图。大量跨任务评测（包括三维指代分割、三维视觉问答和三维开放词表理解）展示了 GenSplat 的最优性能与强泛化能力。我们将开源代码。
英文原文摘要 1491 字符
In this paper, we propose GenSplat, a novel approach for language comprehension in 3D Gaussian Splatting (3DGS). Unlike previous methods that either achieve cross-scene generalization by being bounded to a predefined vocabulary or handle free-form language by overfitting to individual scenes, GenSplat is robust to free-form language queries and generalizable across 3DGS scene representations. Our key insight for this problem is to formulate a structured learning process to progressively align linguistic concepts with 3D Gaussians. It contains two novel technical contributions. First, we propose a Progressive Language Grounding Curriculum that structurally guides the model through learning category-level semantics to instance-level concepts and free-form language, preventing overfitting by building a generalizable language feature space. Second, we design a Multi-modal Large Language Models (MLLM)-guided Reasoning Module that leverages MLLM's semantic and spatial priors to enhance 3D localization and reasoning. To further improve spatial alignment and computational efficiency, we introduce a GeometryAware Frame Selector (GAFS), which adaptively selects the most informative views based on Gaussian and textural cues. Extensive cross-task evaluations (including 3D referring segmentation, 3D visual question answering, and 3D open-vocabulary understanding) demonstrate state-of-the-art performances and strong generalization capability of GenSplat. We will release the codes.