Camera Splatting for Continuous View Optimization
This addresses view synthesis for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles novel view synthesis by modeling cameras as 3D Gaussians and optimizing them to capture view-dependent effects, resulting in superior performance over Farthest View Sampling in handling metallic reflections and textures.
We propose Camera Splatting, a novel view optimization framework for novel view synthesis. Each camera is modeled as a 3D Gaussian, referred to as a camera splat, and virtual cameras, termed point cameras, are placed at 3D points sampled near the surface to observe the distribution of camera splats. View optimization is achieved by continuously and differentiably refining the camera splats so that desirable target distributions are observed from the point cameras, in a manner similar to the original 3D Gaussian splatting. Compared to the Farthest View Sampling (FVS) approach, our optimized views demonstrate superior performance in capturing complex view-dependent phenomena, including intense metallic reflections and intricate textures such as text.