Fast Image-based Neural Relighting with Translucency-Reflection Modeling
This work addresses the challenge of efficient relighting for non-opaque materials in computer graphics, offering a practical solution for applications requiring realistic rendering.
The paper tackles the problem of computationally expensive image-based lighting for translucent materials by presenting a fast neural 3D reconstruction and relighting model that handles translucency and glossy reflections, achieving rendering times of 0.72s on an NVIDIA 3090 GPU and 0.30s on an A100 GPU at 800x800 resolution.
Image-based lighting (IBL) is a widely used technique that renders objects using a high dynamic range image or environment map. However, aggregating the irradiance at the object's surface is computationally expensive, in particular for non-opaque, translucent materials that require volumetric rendering techniques. In this paper we present a fast neural 3D reconstruction and relighting model that extends volumetric implicit models such as neural radiance fields to be relightable using IBL. It is general enough to handle materials that exhibit complex light transport effects, such as translucency and glossy reflections from detailed surface geometry, producing realistic and compelling results. Rendering can be within a second at 800$\times$800 resolution (0.72s on an NVIDIA 3090 GPU and 0.30s on an A100 GPU) without engineering optimization. Our code and dataset are available at https://zhusz.github.io/TRHM-Webpage/.