SA '23: SIGGRAPH Asia 2023 Courses

The emphasis of this course focuses on the capabilities of the WebGL application programming interface (i.e., programming library, often called an API).

Coding empowers automation. Scripts can handle mundane and repetitive tasks in an efficient and precise manner. This course will offer a glimpse into the power of using scripting in Python to automate animation-related tasks in Autodesk Maya using a hands-on interactive format. Attendees will learn how to streamline simple tasks using the magic of scripting. The course will cover Setting up the Python environment in Maya, executing Python commands in the Script Editor, manipulating objects using Python scripting, querying animation data, keyframe manipulation, and creating and modifying. By the end of the course, attendees should walk away with a strong understanding of how the Python language, Maya commands and the ability to write scripts for animating in Maya. Hopefully, they will have the tools, confidence, and initiative to explore more advanced scripts independently. Attendees should have Autodesk Maya, Python, and Visual Studio Code pre-loaded on their devices if they intend to follow along.

The Laplace-Beltrami operator is one of the essential tools in geometric processing. It allows us to solve numerous partial differential equations on discrete surface and volume meshes, which is a fundamental building block in many computer graphics applications. Discrete Laplacians are typically limited to standard elements like triangles or quadrilaterals, which severely constrains the tessellation of the mesh. But in recent years, several approaches were able to generalize the Laplace Beltrami and its closely related gradient and divergence operators to more general meshes. This allows artists and engineers to work with a wider range of elements which are sometimes required and beneficial in their field. This course, which extends the state-of-the-art report by Bunge and Botsch [2023], discusses the different constructions of these three ubiquitous differential operators on arbitrary polygons and polyhedra and analyzes their individual advantages and properties in common computer graphics applications.

Our course provides an essential overview of 3D reconstruction and generative AI-based 3D generation approaches that have transformed the field. The course provides an understanding of the fundamentals of photogrammetry, neural radiance fields-based techniques such as Instant NeRF, and generative AI-based 3D generation such as text-to-3D, with a focus on reflecting on these approaches, their applications in 3D world building, and how participants can integrate them into their research.

The course firstly introduces the core concepts of photogrammetry, through which participants can understand its importance in reconstructing accurate 3D models. Through case studies, participants will reflect on the applications of photogrammetry in various domains, such as cultural heritage preservation and VR experiences, and can view some examples themselves.

We then delve into a gentle introduction to neural rendering with a broad overview of NVIDIA Instant NeRF, a state-of-the-art technique for real-time 3D reconstruction from multiple images. Participants will have the opportunity to watch several demonstrations of InstantNGP and discover its applications in interactive 3D world building.

Furthermore, participants will be introduced to emerging generative AI approaches that simplify 3D content generation. In particular, we explore the use of text-to-3D techniques, which leverage natural language descriptions to automatically generate 3D models. We will also examine the impact of generative AI techniques on the creation of realistic and immersive 3D environments.

By the end of the course, participants will have a solid understanding of the basics of two salient 3D reconstruction methods, as well as other generative AI techniques for 3D content. We also hope to enable participants to critically evaluate and harness the potential of these approaches in 3D world building.

Various parallel algorithms can be decomposed into programming primitives that share similar patterns. This course focuses on studying these programming primitives and their applicability in computer graphics, specifically in the context of massively parallel processing on GPUs. The course begins by establishing a theoretical foundation, followed by practical examples and real-world applications. We explain two pivotal algorithms: parallel reduction and parallel prefix scan in detail, discussing their variants and different implementations. Afterward, we provide a collection of more advanced techniques and tricks applicable across various domains. At the end of the course, we also briefly discuss code optimization.

Use and development of computer systems that are able to learn and adapt without following explicit instructions by using algorithms and statistical models to analyze and draw inferences from patterns in data.

What an AI powered future might look like? Rapid evolution of computing capabilities enables transforming process of scientific discovery and inventing new ways to experience and interact with simulation outcomes in real-time, especially in the context of modern Digital Twins.