RI: Large: Collaborative Research: Reconstructive recognition: Uniting statistical scene understanding and physics-based visual reasoning

RI：大型：协作研究：重建识别：结合统计场景理解和基于物理的视觉推理

基本信息

批准号：
1212928
负责人：
Todd Zickler
金额：
$ 109.09万
依托单位：
Harvard University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2012
资助国家：
美国
起止时间：
2012-10-01 至 2018-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1212928&HistoricalAwards=false
关键词：
RI Large Collaborative Research Reconstructive

项目摘要

This project is creating a novel paradigm for computer vision, termed "reconstructive recognition", that incorporates the strongest elements of previous machine learning-based recognition efforts and the strongest elements of previous reconstruction efforts based on radiometric reasoning. The goal is to provide a new foundation for machine perception, and the potential for a transformative advance in applications of computer vision. The project seeks novel physics-based methods for recognition as well as novel learning-based methods for interpreting pixel values in terms of the physics of a scene. The agenda is structured around four aims: Aim I develops generalized reconstructive processes that unify the recovery of shape, materials, motion and illumination. Aim II focuses on supervised visual learning methods that exploit such reconstructive image representations. Aim III pursues unsupervised discovery of reconstructive representations that converge to be similar to the engineered models of Aim I. Finally, Aim IV introduces well-defined challenge problems that focus the field and serve as measurable proxies for progress in computer vision applications that have high potential impact on society. There is a significant broader impact to this project, not least being the improvement in computer vision pedagogy that ensues from a reunification of the currently divergent recognition and reconstruction views of the field. More broadly, this project pursues critical steps toward a future where machines can see, a future that will bring changes to robotics, human-computer interfaces, security, and autonomous navigation, to name a few.

该项目正在为计算机视觉创建一种新颖的范式，称为“重建性识别”，该项目结合了以前基于机器学习的识别工作的最强元素，以及基于放射学推理的先前重建工作的最强元素。目的是为机器感知提供新的基础，并在计算机视觉应用中实现变革性进步的潜力。该项目寻求新颖的基于物理学的方法来识别识别，以及基于学习的新方法来解释场景的物理学。该议程围绕四个目标结构：目标我开发了统一形状，材料，运动和照明的恢复的广义重建过程。 AIM II专注于受监督的视觉学习方法，这些方法利用了此类重建图像表示。 AIM III追求无监督的重建表示形式，这些表示与AIM I的工程模型相似。最后，AIM IV引入了定义明确的挑战问题，这些问题集中在该领域，并作为对社会潜在影响很大的计算机视觉应用程序的可衡量代理。对该项目有更大的影响，尤其是计算机视觉教学法的改善，这是由于对当前不同的认识和对该领域的重建观点的统一而随之而来的。从更广泛的角度来看，该项目采取了关键的步骤，迈向了机器可以看到的未来，这将为机器人技术，人力计算机界面，安全性和自治导航带来变化，仅举几例。