Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

TL;DR

This paper introduces Neural Directional Encoding (NDE), a novel view-dependent appearance encoding for neural radiance fields that significantly improves the synthesis of specular objects by modeling high-frequency angular signals and interreflection effects, enabling real-time rendering.

Contribution

The paper proposes Neural Directional Encoding (NDE), a new angular and spatial encoding method for NeRFs that enhances modeling of specular reflections and interreflections, outperforming previous approaches.

Findings

NDE outperforms state-of-the-art methods on synthetic and real datasets.

NDE enables fast, real-time inference with small neural networks.

NDE effectively models high-frequency angular signals and interreflection effects.

Abstract

Novel-view synthesis of specular objects like shiny metals or glossy paints remains a significant challenge. Not only the glossy appearance but also global illumination effects, including reflections of other objects in the environment, are critical components to faithfully reproduce a scene. In this paper, we present Neural Directional Encoding (NDE), a view-dependent appearance encoding of neural radiance fields (NeRF) for rendering specular objects. NDE transfers the concept of feature-grid-based spatial encoding to the angular domain, significantly improving the ability to model high-frequency angular signals. In contrast to previous methods that use encoding functions with only angular input, we additionally cone-trace spatial features to obtain a spatially varying directional encoding, which addresses the challenging interreflection effects. Extensive experiments on both synthetic and real datasets show that a NeRF model with NDE (1) outperforms the state of the art on view synthesis of specular objects, and (2) works with small networks to allow fast (real-time) inference. The project webpage and source code are available at: \url{https://lwwu2.github.io/nde/}.