SpatialSplat：从稀疏无位姿图像高效生成语义三维
SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images
AI总结：
提出SpatialSplat前馈框架，利用双场语义表示和选择性高斯机制，从稀疏无位姿图像高效生成紧凑语义三维，减少60%参数且性能优于现有方法。
摘要：
三维重建领域的一个重大突破是前馈范式，该范式能够从稀疏、无位姿的图像中生成逐像素的三维点或高斯原语。为了进一步融入语义信息，同时避免高维语义特征带来的显著内存和存储开销，现有方法通过将每个原语与压缩的语义特征向量关联来扩展这一范式。然而，这些方法存在两个主要局限：（a）朴素压缩的特征损害了表达力，影响模型捕获细粒度语义的能力；（b）逐像素的原语预测在重叠区域引入冗余，造成不必要的内存开销。为此，我们提出了SpatialSplat，一种前馈框架，它生成冗余感知的高斯，并利用双场语义表示。特别地，基于同一实例内的原语表现出高度语义一致性的洞察，我们将语义表示分解为粗粒度特征场和细粒度但低维的特征场，前者以最少原语编码未压缩的语义，后者捕获详细的实例间关系。此外，我们提出了一种选择性高斯机制，仅保留场景中必要的高斯，有效消除冗余原语。我们提出的SpatialSplat以更紧凑的三维高斯学习准确的语义信息和详细的实例先验，使语义三维重建更具实用性。我们进行了大量实验来评估我们的方法，结果表明在场景表示参数上显著减少了60%，同时实现了优于最先进方法的性能。代码可在https://github.com/shengyuuu/SpatialSplat.git获取。
英文摘要：
A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate semantics while avoiding the significant memory and storage costs of high-dimensional semantic features, existing methods extend this paradigm by associating each primitive with a compressed semantic feature vector. However, these methods have two major limitations: (a) the naively compressed feature compromises expressiveness, affecting the model's ability to capture fine-grained semantics, and (b) the pixel-wise primitive prediction introduces redundancy in overlapping areas, causing unnecessary memory overhead. To this end, we introduce \textbf{SpatialSplat}, a feedforward framework that produces redundancy-aware Gaussians and capitalizes on a dual-field semantic representation. Particularly, with the insight that primitives within the same instance exhibit high semantic consistency, we decompose the semantic representation into a coarse feature field that encodes uncompressed semantics with minimal primitives, and a fine-grained yet low-dimensional feature field that captures detailed inter-instance relationships. Moreover, we propose a selective Gaussian mechanism, which retains only essential Gaussians in the scene, effectively eliminating redundant primitives. Our proposed Spatialsplat learns accurate semantic information and detailed instances prior with more compact 3D Gaussians, making semantic 3D reconstruction more applicable. We conduct extensive experiments to evaluate our method, demonstrating a remarkable 60\% reduction in scene representation parameters while achieving superior performance over state-of-the-art methods. The code is available at https://github.com/shengyuuu/SpatialSplat.git
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。
