NeRF-SR: High-Quality Neural Radiance Fields using Supersampling

Understand

We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs.

• Our method is built upon Neural Radiance Fields (NeRF) that predicts per-point density and color with a multi-layer perceptron.
• While producing images at arbitrary scales, NeRF struggles with resolutions that go beyond observed images.
• Our key insight is that NeRF benefits from 3D consistency, which means an observed pixel absorbs information from nearby views.