NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections

TL;DR

NeRF-Casting introduces a ray tracing-based method that enhances the rendering of view-dependent specular reflections in neural radiance fields, achieving photorealistic results efficiently.

Contribution

The paper proposes a novel reflection ray casting approach that models view-dependent appearance with consistent reflections using a small neural network, improving realism and efficiency.

Findings

Outperforms prior methods in rendering shiny objects.

Synthesizes photorealistic specular reflections in real-world scenes.

Operates with comparable optimization time to current state-of-the-art models.

Abstract

Neural Radiance Fields (NeRFs) typically struggle to reconstruct and render highly specular objects, whose appearance varies quickly with changes in viewpoint. Recent works have improved NeRF's ability to render detailed specular appearance of distant environment illumination, but are unable to synthesize consistent reflections of closer content. Moreover, these techniques rely on large computationally-expensive neural networks to model outgoing radiance, which severely limits optimization and rendering speed. We address these issues with an approach based on ray tracing: instead of querying an expensive neural network for the outgoing view-dependent radiance at points along each camera ray, our model casts reflection rays from these points and traces them through the NeRF representation to render feature vectors which are decoded into color using a small inexpensive network. We demonstrate that our model outperforms prior methods for view synthesis of scenes containing shiny objects, and that it is the only existing NeRF method that can synthesize photorealistic specular appearance and reflections in real-world scenes, while requiring comparable optimization time to current state-of-the-art view synthesis models.