C³-GS：学习面向可泛化高斯泼溅的上下文感知、跨维度与跨尺度特征
${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting
AI总结：
针对可泛化高斯泼溅在稀疏视角下特征一致性与几何建模不足的问题，本文提出 C³-GS，通过上下文感知、跨维度和跨尺度约束增强特征学习，实现最先进的渲染质量与泛化能力。
摘要：
可泛化高斯泼溅（Generalizable Gaussian Splatting）旨在无需逐场景优化即可为未见场景合成新视角。特别是，近期进展利用前馈网络预测逐像素高斯参数，从而能够基于稀疏输入视角实现高质量合成。然而，现有方法在为高斯预测编码具有判别性且多视角一致的特征方面存在不足，在稀疏视角下难以构建准确几何。为解决这一问题，我们提出 C³-GS，该框架通过引入上下文感知、跨维度和跨尺度约束来增强特征学习。其架构将三个轻量级模块集成到统一渲染管线中，改进特征融合，并在无需额外监督的情况下实现照片级真实感合成。在基准数据集上的大量实验验证，C³-GS 取得了最先进的渲染质量和泛化能力。代码位于：https://github.com/YuhsiHu/C3-GS。
英文摘要：
Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization. In particular, recent advancements utilize feed-forward networks to predict per-pixel Gaussian parameters, enabling high-quality synthesis from sparse input views. However, existing approaches fall short in encoding discriminative, multi-view consistent features for Gaussian predictions, which struggle to construct accurate geometry with sparse views. To address this, we propose $\mathbf{C}^{3}$-GS, a framework that enhances feature learning by incorporating context-aware, cross-dimension, and cross-scale constraints. Our architecture integrates three lightweight modules into a unified rendering pipeline, improving feature fusion and enabling photorealistic synthesis without requiring additional supervision. Extensive experiments on benchmark datasets validate that $\mathbf{C}^{3}$-GS achieves state-of-the-art rendering quality and generalization ability. Code is available at: https://github.com/YuhsiHu/C3-GS.
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。
