L0-Sampler: An L0Model Guided Volume Sampling for NeRF

Figure 1. We present L0-Sampler, an upgrade of the Hierarchical Volume Sampling strategy of NeRF. By testing on different datasets, our proposed L0-Sampler with different NeRF frameworks can achieve stable performance improvements on rendering and reconstruction tasks with few lines of code modifications and around the same training time. Left: Results comparison between works with original HVS and our L0-Sampler. Right: Instead of using piecewise constant functions when fitting w(t), we use piecewise exponential functions for interpolation to get a quasi-L0 w(t), resulting in more concentrated and precise sampling.