Learning Generative Models of 3D Shapes and Environments

学习 3D 形状和环境的生成模型

• 批准号: RGPIN-2019-07098
• 负责人: Zhang, Hao
• 金额: $ 4.66万
• 依托单位: Simon Fraser University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=750590
• 关键词: Learning; Generative; Models; 3D; Shapes

One of the most intriguing and reoccurring questions in AI and computer science is when a machine can be considered to possess human-level intelligence. In its best-known version, the Turing Test judges the humanness of a machine by its ability to make natural language conversations. In 2014, a chatbot named Eugene was considered by many to have passed the test. So is Turing Test the best choice? Is it too easy? In the lesser-known "Lovelace Test", named after Lady Ada Lovelace, machines are judged by their creativity or originality. Lovelace pre-dated Turing by about 100 years and is often credited as the world's first computer programmer. In 1843, she remarked that computers cannot be thought to possess human intelligence until they can generate something original, which they were not programmed to do. Can a machine truly become creative? That is the ultimate question and the long-term pursuit would be to close the gap between machines and humans in creativity. In the shorter term, and as a computer graphics researcher, I want to tackle a more tangible problem first: to train machines to learn and execute generative models of 3D shapes and environments, where the outcomes do not have to be creative. While classical graphics mainly focuses on realistic image synthesis from explicit scene descriptions, in the new era of graphics, we wish to synthesize all forms of visual contents, where the inputs can be abstract (e.g., texts) or consist of only a set of exemplars. My current research objective is to advance data-driven visual content creation and geometric deep learning, making "big 3D data" a reality and fulfilling my four V's for data generation. Namely, the generated data should be in large volume and with cross-category variety, intra-category variation, and novelty - and ultimately, originality, to pass the Lovelace Test. In the next five years, I will advance the state of the art in developing and training generative models for 3D shapes and environments, enriching visual contents and design prototypes to serve applications in AR/VR, robotics, education, health, smart homes, and design and manufacturing. As well, I will keep pushing the boundary of computational creativity.

在人工智能和计算机科学中，最有趣、最反复出现的问题之一是，一台机器何时可以被认为拥有人类水平的智能。在其最著名的版本中，图灵测试通过机器进行自然语言对话的能力来判断机器是否人性化。2014年，一个名叫尤金的聊天机器人被许多人认为通过了测试。那么图灵测试是最好的选择吗？是不是太简单了？在以Ada Lovelace女士命名的不太为人所知的“Lovelace测试”中，机器的评判标准是它们的创造力或独创性。洛夫莱斯比图灵早了大约100年，通常被认为是世界上第一个计算机程序员。1843年，她指出，除非计算机能够产生一些原始的东西，而这些东西并不是编程赋予它们的，否则它们就不能被认为拥有人类的智慧。机器真的能变得有创造力吗？这是最终的问题，而长期的追求将是缩小机器与人类在创造力方面的差距。在短期内，作为一名计算机图形学研究人员，我想首先解决一个更切实的问题：训练机器学习和执行3D形状和环境的生成模型，其结果不必是创造性的。经典图形学主要侧重于从明确的场景描述中合成逼真的图像，而在图形学的新时代，我们希望合成所有形式的视觉内容，其中输入可以是抽象的（例如文本）或仅由一组范例组成。我目前的研究目标是推进数据驱动的视觉内容创作和几何深度学习，使“大3D数据”成为现实，实现我对数据生成的四个V。也就是说，生成的数据应该是大量的，具有跨类别的多样性，类别内的变化，以及新颖性，最终是独创性，以通过Lovelace测试。在接下来的五年里，我将在开发和培训3D形状和环境的生成模型方面推进最先进的技术，丰富视觉内容和设计原型，以服务于AR/VR、机器人、教育、健康、智能家居、设计和制造等领域的应用。同时，我将继续推动计算创造力的边界。