Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
This work addresses the problem of realistic global illumination for real-time virtual environments, representing an incremental improvement with a novel network architecture.
The paper tackles the challenge of capturing long-range indirect illumination in real-time rendering by introducing a learning-based estimator that predicts diffuse indirect illumination in screen space, achieving superior performance over previous learning-based techniques in handling complex lighting and new scenes.
Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.