PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation
This work addresses the problem of efficient neural representation for large-scale outdoor scenes, which is incremental as it builds on existing implicit neural representation methods by incorporating point cloud priors.
The paper tackles the challenge of representing and synthesizing detailed textures in unbounded large-scale outdoor scenes by proposing a Point Diffusion Implicit Function (PDF) that uses a diffusion module to enhance sparse point clouds into dense priors, reducing the sampling space to the scene surface, and it outperforms state-of-the-art baselines in novel view synthesis.
Recent advances in implicit neural representations have achieved impressive results by sampling and fusing individual points along sampling rays in the sampling space. However, due to the explosively growing sampling space, finely representing and synthesizing detailed textures remains a challenge for unbounded large-scale outdoor scenes. To alleviate the dilemma of using individual points to perceive the entire colossal space, we explore learning the surface distribution of the scene to provide structural priors and reduce the samplable space and propose a Point Diffusion implicit Function, PDF, for large-scale scene neural representation. The core of our method is a large-scale point cloud super-resolution diffusion module that enhances the sparse point cloud reconstructed from several training images into a dense point cloud as an explicit prior. Then in the rendering stage, only sampling points with prior points within the sampling radius are retained. That is, the sampling space is reduced from the unbounded space to the scene surface. Meanwhile, to fill in the background of the scene that cannot be provided by point clouds, the region sampling based on Mip-NeRF 360 is employed to model the background representation. Expensive experiments have demonstrated the effectiveness of our method for large-scale scene novel view synthesis, which outperforms relevant state-of-the-art baselines.