Accelerating Neural Field Training via Soft Mining

https://ubc-vision.github.io/nf-soft-mining/ Figure 1. Teaser: we introduce "soft mining" to accelerate neural field training. When applied to Neural Radiance Field (NeRF) training, our method significantly improves convergence. We visualize the error maps (blue denotes low error and red denotes high error) and the rendered novel views for uniform sampling and our method. We plot the convergence showing the Peak Signal-to-Noise Ratio (PSNR) for the corresponding scene. We render both images at 1k iterations of training, specified by the red dashed line in the (right) graph. Our method achieves the same PSNR significantly faster than the baselines.