We introduce a 3D object extraction method for Gaussian Splatting that prunes irrelevant primitives using K-nearest neighbors analysis and compensates for occlusions with diffusion-based generative inpainting.
We cast an hourglass as an additional training ray, which adaptively regularizes the high-frequency components of the samples, and enhance the integrity of training framework by conceptualizing the hourglass as a bundle of flipped diffuse reflection rays, aligning with the Lambertian assumption.
We simplify outdoor scene relighting for NeRF by aligning with the sun, eliminating the need for environment maps and speeding up the process using a novel cubemap concept within the framework of TensoRF.
We utilize the flipped reflection rays as additional training resources for the few-shot novel view synthesis, leading to more accurate surface normal estimation.
We model a ray with mixture density model, leading to efficient learning of density distribution with sparse inputs, and propose an effective auxiliary task of ray depth estimation for few-shot novel view synthesis.