Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids

TL;DR

Rip-NeRF introduces a novel Ripmap-Encoded Platonic Solid method to improve anti-aliasing in neural radiance fields, effectively capturing anisotropic details for high-fidelity rendering.

Contribution

The paper proposes a new representation combining Platonic Solid Projection and Ripmap encoding to enhance anti-aliasing in NeRFs, addressing anisotropic area characterization.

Findings

Achieves state-of-the-art rendering quality on synthetic and real-world datasets.

Excels in rendering fine details of textures and repetitive structures.

Maintains relatively swift training times.

Abstract

Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characterize anisotropic areas induced by the cone-casting procedure. This paper introduces a Ripmap-Encoded Platonic Solid representation to precisely and efficiently featurize 3D anisotropic areas, achieving high-fidelity anti-aliasing renderings. Central to our approach are two key components: Platonic Solid Projection and Ripmap encoding. The Platonic Solid Projection factorizes the 3D space onto the unparalleled faces of a certain Platonic solid, such that the anisotropic 3D areas can be projected onto planes with distinguishable characterization. Meanwhile, each face of the Platonic solid is encoded by the Ripmap encoding, which is constructed by anisotropically pre-filtering a learnable feature grid, to enable featurzing the projected anisotropic areas both precisely and efficiently by the anisotropic area-sampling. Extensive experiments on both well-established synthetic datasets and a newly captured real-world dataset demonstrate that our Rip-NeRF attains state-of-the-art rendering quality, particularly excelling in the fine details of repetitive structures and textures, while maintaining relatively swift training times.