LangFlash: 基于前馈的3D语言高斯泼溅从稀疏无位姿图像
LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images
AI总结：
提出LangFlash，一种前馈框架，从稀疏无位姿多视图图像直接预测3D高斯原语及其语言对齐语义特征，实现低延迟3D重建和语义一致场景理解。
摘要：
我们提出LangFlash，一种用于3D语言高斯泼溅的前馈框架，它从稀疏无位姿多视图图像重建由高斯原语参数化的3D场景，这些原语富含语言对齐的语义特征。与基于优化的3D方法不同，LangFlash在单次前向传播中直接预测几何和语义，实现低延迟3D重建和语言一致的场景理解。为了支持大规模训练，我们为RealEstate10k数据集丰富了连贯且密集的语义信息，用于3D语义监督。此外，我们提出了一种稀疏语义编码方案，该方案将全局语义字典与局部变化的每个原语权重相结合，在保留高级语言信息的同时降低表示复杂度。实验结果表明，与先前方法相比，LangFlash在新视图合成和语义一致性方面表现更优。本研究为无位姿、语言基础的3D场景重建建立了新范式，推动了可泛化3D视觉和多模态场景理解的发展。演示地址：https://liylo.github.io/langflash.github.io/。
英文摘要：
We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images. Unlike optimization-based 3D methods, LangFlash directly predicts the geometry and semantics in a single forward pass, enabling low-latency 3D reconstruction and language-consistent scene understanding. To support large-scale training, we enriched the RealEstate10k dataset with coherent and dense semantic information for 3D semantic supervision. Furthermore, we propose a sparse semantic encoding scheme that combines a global semantic dictionary with locally varying per-primitive weights, preserving high-level linguistic information, while reducing representation complexity. Experimental results show that LangFlash achieves superior novel view synthesis and semantic consistency compared with previous methods. This study establishes a new paradigm for pose-free, language-grounded 3D scene reconstruction, advancing generalizable 3D vision and multimodal scene understanding. Demo is available at https://liylo.github.io/langflash.github.io/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
