The recent success of Machine Learning encouraged research using artificial neural networks (NNs) in computer graphics. A good example is the bidirectional texture function (BTF), a data-driven representation of surface materials that can encapsulate complex behaviors that would otherwise be too expensive to calculate for real-time applications, such as self-shadowing and interreflections. We propose two changes to the state-of-the-art using neural networks for BTFs, specifically NeuMIP. These changes, suggested by recent work in neural scene representation and rendering, aim to improve baseline quality, memory footprint, and performance. We conduct an ablation study to evaluate the impact of each change. We test both synthetic and real data, and provide a working implementation within the Mitsuba 2 rendering framework. Our results show that our method outperforms the baseline in all these metrics and that neural BTF is part of the broader field of neural scene representation. Project website: https://traverse-research.github.io/NeuBTF/.
DOCUMENT
In this paper, I first discuss in some detail the current use of Learning Objects and show it to be wanting. Although their use, in principle, may offer much flexibility in creating content, in practice it will not, particularly since it does not support sufficient pedagogical flexibility. Then I offer an alternative view which, in my view, is indeed capable of fulfilling all the needs of customised learning, both the need for custom content and the need for custom pedagogies. I conclude by addressing some possible criticisms of my line of reasoning. This Chapter is a remake of Necessary Conditions for the Flexible Reuse of Educational Content.
DOCUMENT
