Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling
This addresses the problem of accurately rendering shiny or glossy objects in computer graphics, with incremental improvements over existing methods.
The paper tackles the challenge of novel-view synthesis for specular objects by introducing Neural Directional Encoding (NDE), which improves NeRF's ability to model high-frequency angular signals and interreflection effects, resulting in state-of-the-art performance and real-time inference.
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/}.