Efficient Ray Sampling for Radiance Fields Reconstruction
This work addresses training efficiency for NeRF models, which is crucial for practical applications in 3D scene reconstruction, though it is incremental as it builds on existing NeRF frameworks.
The paper tackles the problem of slow training in neural radiance fields by proposing a novel ray sampling method that reduces redundancy, achieving faster convergence and improved rendering quality, especially in texture-complex regions, as demonstrated by outperforming state-of-the-art techniques on benchmarks.
Accelerating neural radiance fields training is of substantial practical value, as the ray sampling strategy profoundly impacts network convergence. More efficient ray sampling can thus directly enhance existing NeRF models' training efficiency. We therefore propose a novel ray sampling approach for neural radiance fields that improves training efficiency while retaining photorealistic rendering results. First, we analyze the relationship between the pixel loss distribution of sampled rays and rendering quality. This reveals redundancy in the original NeRF's uniform ray sampling. Guided by this finding, we develop a sampling method leveraging pixel regions and depth boundaries. Our main idea is to sample fewer rays in training views, yet with each ray more informative for scene fitting. Sampling probability increases in pixel areas exhibiting significant color and depth variation, greatly reducing wasteful rays from other regions without sacrificing precision. Through this method, not only can the convergence of the network be accelerated, but the spatial geometry of a scene can also be perceived more accurately. Rendering outputs are enhanced, especially for texture-complex regions. Experiments demonstrate that our method significantly outperforms state-of-the-art techniques on public benchmark datasets.