分位数渲染：高效嵌入高维特征到3D高斯点散射
Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting
AI总结：
分位数渲染通过高效处理高维特征提升3D高斯点散射的渲染效率和保真度，实现更高质量的开放词汇分割。
摘要：
最近计算机视觉领域的进展已成功将开放词汇分割（OVS）扩展到3D领域，通过利用3D高斯点散射（3D-GS）。尽管取得了进展，但高效渲染用于开放词汇查询所需的高维特征仍是一个重大挑战。现有方法采用代码本或特征压缩，导致信息丢失，从而降低分割质量。为了解决这一限制，我们引入了分位数渲染（Q-Render），一种新的3D高斯渲染策略，能够高效处理高维特征同时保持高保真度。与传统体积渲染不同，后者密集采样每个射线所有3D高斯点，Q-Render仅稀疏采样那些在射线上有主导影响的点。通过将Q-Render集成到通用的3D神经网络中，我们还提出了高斯点散射网络（GS-Net），该网络以通用的方式预测高斯特征。在ScanNet和LeRF上的广泛实验表明，我们的框架优于最先进的方法，同时在512-D特征图上实现了约43.7倍的速度提升。代码将公开发布。
英文摘要：
Recent advancements in computer vision have successfully extended Open-vocabulary segmentation (OVS) to the 3D domain by leveraging 3D Gaussian Splatting (3D-GS). Despite this progress, efficiently rendering the high-dimensional features required for open-vocabulary queries poses a significant challenge. Existing methods employ codebooks or feature compression, causing information loss, thereby degrading segmentation quality. To address this limitation, we introduce Quantile Rendering (Q-Render), a novel rendering strategy for 3D Gaussians that efficiently handles high-dimensional features while maintaining high fidelity. Unlike conventional volume rendering, which densely samples all 3D Gaussians intersecting each ray, Q-Render sparsely samples only those with dominant influence along the ray. By integrating Q-Render into a generalizable 3D neural network, we also propose Gaussian Splatting Network (GS-Net), which predicts Gaussian features in a generalizable manner. Extensive experiments on ScanNet and LeRF demonstrate that our framework outperforms state-of-the-art methods, while enabling real-time rendering with an approximate ~43.7x speedup on 512-D feature maps. Code will be made publicly available.
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。
