Efficient neural supersampling on a novel gaming dataset
This work addresses the need for higher resolutions and framerates in video game rendering, though it is incremental as it builds on existing supersampling techniques.
The authors tackled the challenge of real-time rendering for video games by developing a neural supersampling algorithm that is 4 times more efficient than existing methods while maintaining accuracy, and they introduced a novel gaming dataset with auxiliary modalities like motion vectors and depth.
Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a novel neural algorithm for supersampling rendered content that is 4 times more efficient than existing methods while maintaining the same level of accuracy. Additionally, we introduce a new dataset which provides auxiliary modalities such as motion vectors and depth generated using graphics rendering features like viewport jittering and mipmap biasing at different resolutions. We believe that this dataset fills a gap in the current dataset landscape and can serve as a valuable resource to help measure progress in the field and advance the state-of-the-art in super-resolution techniques for gaming content.