Freq-Mip-AA : Frequency Mip Representation for Anti-Aliasing Neural Radiance Fields

TL;DR

FreqMipAA introduces a frequency-domain anti-aliasing method for Neural Radiance Fields that uses scale-specific low-pass filters and learnable masks, significantly reducing aliasing artifacts and improving rendering quality.

Contribution

This work presents a novel frequency-based anti-aliasing technique for grid-based NeRFs, enabling faster training and better detail preservation compared to previous methods.

Findings

Effectively eliminates aliasing artifacts in NeRF rendering.

Achieves state-of-the-art results on multi-scale Blender dataset.

Faster training times due to grid-based representation.

Abstract

Neural Radiance Fields (NeRF) have shown remarkable success in representing 3D scenes and generating novel views. However, they often struggle with aliasing artifacts, especially when rendering images from different camera distances from the training views. To address the issue, Mip-NeRF proposed using volumetric frustums to render a pixel and suggested integrated positional encoding (IPE). While effective, this approach requires long training times due to its reliance on MLP architecture. In this work, we propose a novel anti-aliasing technique that utilizes grid-based representations, usually showing significantly faster training time. In addition, we exploit frequency-domain representation to handle the aliasing problem inspired by the sampling theorem. The proposed method, FreqMipAA, utilizes scale-specific low-pass filtering (LPF) and learnable frequency masks. Scale-specific low-pass filters (LPF) prevent aliasing and prioritize important image details, and learnable masks effectively remove problematic high-frequency elements while retaining essential information. By employing a scale-specific LPF and trainable masks, FreqMipAA can effectively eliminate the aliasing factor while retaining important details. We validated the proposed technique by incorporating it into a widely used grid-based method. The experimental results have shown that the FreqMipAA effectively resolved the aliasing issues and achieved state-of-the-art results in the multi-scale Blender dataset. Our code is available at https://github.com/yi0109/FreqMipAA .