用可学习的纹理平面块替代高斯点，提升新视角合成质量与效率。
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
- 用可优化的纹理平面块表示场景，替代传统高斯点
- 在DTU数据集上达29.72的PSNR，超越2D和3D高斯点渲染
- 平面结构支持光线追踪效果，压缩后存储降低17倍
我们提出一种新型新视角合成方法——海报式点云（BBSplat），通过可学习的纹理平面块表示场景。这些平面块具有可优化的RGB纹理和透明度图，用于控制形状，可直接替换任意高斯点渲染流程中的高斯点。该方法弥合了2D与3D高斯点渲染的质量差距，实现了如2DGS框架般精确的3D网格提取。同时，平面结构支持光栅化中的光线追踪效果。新增正则项促使纹理更稀疏，实现高达17倍的模型存储压缩。在真实室内与室外场景标准数据集（Tanks&Temples、DTU、Mip-NeRF-360）上的实验表明，BBSplat在全高清分辨率下于DTU数据集达到29.72的最优PSNR。
原文摘要 · Abstract (English)
We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable textured planar primitives with learnable RGB textures and alpha-maps to control their shape. BBSplat primitives can be used in any Gaussian Splatting pipeline as drop-in replacements for Gaussians. The proposed primitives close the rendering quality gap between 2D and 3D Gaussian Splatting (GS), enabling the accurate extraction of 3D mesh as in the 2DGS framework. Additionally, the explicit nature of planar primitives enables the use of the ray-tracing effects in rasterization. Our novel regularization term encourages textures to have a sparser structure, enabling an efficient compression that leads to a reduction in the storage space of the model up to x17 times compared to 3DGS. Our experiments show the efficiency of BBSplat on standard datasets of real indoor and outdoor scenes such as Tanks&Temples, DTU, and Mip-NeRF-360. Namely, we achieve a state-of-the-art PSNR of 29.72 for DTU at Full HD resolution.
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。