提出量化渲染方法，让3D高维特征高效显存，实时性能提升43.7倍。
Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting
- 按射线主导影响稀疏采样高维特征，避免冗余计算
- 在ScanNet与LeRF上优于现有方法，512维特征图实现实时渲染
- 适用于需要开放词汇3D分割的场景，适合部署于资源受限设备
近期计算机视觉进展已将开放词汇分割（OVS）扩展至3D领域，利用3D高斯点阵（3D-GS）实现。然而，高效渲染用于开放词汇查询的高维特征仍具挑战性。现有方法采用码本或特征压缩，导致信息损失，降低分割质量。为此，我们提出量化渲染（Q-Render），一种新型3D高斯渲染策略，能高效处理高维特征并保持高保真度。与传统体素渲染不同，Q-Render仅稀疏采样沿射线具有主导影响的3D高斯。通过将Q-Render集成到通用3D神经网络中，我们还提出了高斯点阵网络（GS-Net），可泛化预测高斯特征。在ScanNet和LeRF上的大量实验表明，该框架超越当前最优方法，并在512维特征图上实现约43.7倍的速度提升，支持实时渲染。代码将公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。