🤖 AI Summary
Existing 3D Gaussian splatting methods implicitly encode illumination within the geometric representation, hindering physically based global illumination modeling and scene editing. This paper introduces the first screen-space Monte Carlo ray tracing framework tailored for 3D Gaussian representations, explicitly decoupling direct and single-bounce indirect illumination to approximate global illumination in real time during rendering. Crucially, the method operates without modifying the underlying Gaussian parameterization—preserving the original computational efficiency and scene editability. It enables real-time interactive editing of materials, light sources, and viewpoints. Experiments demonstrate that the approach maintains millisecond-level rendering throughput while significantly improving photorealism and accuracy in indirect illumination estimation. By integrating physically grounded light transport simulation with the lightweight, differentiable Gaussian representation, our framework establishes a new paradigm for editable inverse rendering: lightweight, numerically stable, and physically consistent.
📝 Abstract
3D Gaussian Splatting shows great potential in reconstructing photo-realistic 3D scenes. However, these methods typically bake illumination into their representations, limiting their use for physically-based rendering and scene editing. Although recent inverse rendering approaches aim to decompose scenes into material and lighting components, they often rely on simplifying assumptions that fail when editing. We present a novel approach that enables efficient global illumination for 3D Gaussians Splatting through screen-space ray tracing. Our key insight is that a substantial amount of indirect light can be traced back to surfaces visible within the current view frustum. Leveraging this observation, we augment the direct shading computed by 3D Gaussians with Monte-Carlo screen-space ray-tracing to capture one-bounce indirect illumination. In this way, our method enables realistic global illumination without sacrificing the computational efficiency and editability benefits of 3D Gaussians. Through experiments, we show that the screen-space approximation we utilize allows for indirect illumination and supports real-time rendering and editing. Code, data, and models will be made available at our project page: https://wuzirui.github.io/gs-ssr.