从前馈新视角合成中学习紧凑三维表示
Learning Compact 3D Representations from Feed-Forward Novel View Synthesis
用可学习 token 的自注意力模式同时决定高斯生成位置与特征提升，把「紧凑高斯」当作前馈重建与场景理解的共享表示，可直接借鉴到无位姿稀疏视图下的重建-理解一体化管线，降低显存并改善多视图特征聚合。
原文依据 We introduce learnable tokens that aggregate multi-view features through self-attention to guide Gaussian generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论以无位姿稀疏视图为输入、以前馈方式重建并理解三维场景，仍是三维计算机视觉中的一项挑战性任务。近期方法采用逐像素三维高斯泼溅进行重建，随后通过二维到三维的特征提升阶段完成场景理解。然而，这类方法会产生大量冗余高斯，导致显存开销高、多视图特征聚合次优，从而使新视角合成与场景理解性能下降。我们提出 C3G，一种新的前馈框架，仅在关键空间位置估计紧凑的三维高斯，在降低冗余的同时实现有效的特征提升。我们引入可学习 token，通过自注意力聚合多视图特征以引导高斯生成，确保每个高斯整合跨视图的相关视觉特征。随后我们利用学到的注意力模式进行高斯解码，从而高效地提升特征。在无位姿新视角合成、三维开放词表分割以及视图不变特征聚合上的大量实验证明了本方法的有效性。结果表明，紧凑但具有几何意义的表示足以支撑高质量的场景重建与理解，相比现有方法实现了更优的显存效率与特征保真度。
英文原文摘要 1375 字符
Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a 2D-to-3D feature lifting stage for scene understanding. However, they generate excessive redundant Gaussians, causing high memory overhead and sub-optimal multi-view feature aggregation, leading to degraded novel view synthesis and scene understanding performance. We propose C3G, a novel feed-forward framework that estimates compact 3D Gaussians only at essential spatial locations, minimizing redundancy while enabling effective feature lifting. We introduce learnable tokens that aggregate multi-view features through self-attention to guide Gaussian generation, ensuring each Gaussian integrates relevant visual features across views. We then exploit the learned attention patterns for Gaussian decoding to efficiently lift features. Extensive experiments on pose-free novel view synthesis, 3D open-vocabulary segmentation, and view-invariant feature aggregation demonstrate our approach's effectiveness. Results show that a compact yet geometrically meaningful representation is sufficient for high-quality scene reconstruction and understanding, achieving superior memory efficiency and feature fidelity compared to existing methods.