BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
This work improves novel view synthesis for computer vision applications by enabling more efficient and accurate 3D mesh extraction and storage reduction, though it is incremental as it builds on existing Gaussian Splatting frameworks.
The paper tackles novel view synthesis by introducing learnable textured planar primitives that close the rendering quality gap between 2D and 3D Gaussian Splatting, achieving a state-of-the-art PSNR of 29.72 on the DTU dataset at Full HD resolution.
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.