Ravi Ramamoorthi : Sampling and Signal-Processing for High-Dimensional... : CMU Graphics Colloquium

Автор: CMU Robotics Institute

Загружено: 2024-09-06

Просмотров: 1020

Описание:

Carnegie Mellon Graphics Colloquium
Ravi Ramamoorthi
Sampling and Signal-Processing for High-Dimensional Visual Appearance in Computer Graphics and Vision

https://www.ri.cmu.edu/event/sampling...

Ravi Ramamoorthi
Ronald L. Graham Professor of Computer Science Director
University of California, San Diego
September 5, 2024

Abstract: Many problems in computer graphics and vision, such as acquiring images of a scene to enable synthesis of novel views from many directions for virtual reality, computing realistic images by integrating lighting from many different incident directions across a range of scene pixels and viewing angles, or acquiring and modeling the appearance of realistic materials like fur or skin, require sampling and signal-processing on high-dimensional visual appearance spaces involving changes in lighting, viewpoint, spatial location and other parameters. Over my career, my group has developed a number of novel mathematical and signal-processing tools to address these challenges, significantly reducing the cost of acquisition and computation. In this talk, we describe significant theoretical and practical advances in real-time high quality precomputed rendering, Monte Carlo rendering with orders of magnitude fewer samples, and realistic novel view synthesis. In all cases, the methods are now widely deployed in production, and we discuss new computational and signal-processing tools we have developed, including reflection as convolution, sheared and multiple axis-aligned filtering, plenoptic light field sampling and neural radiance fields.
Bio: Ravi Ramamoorthi is the Ronald L. Graham Professor of Computer Science at UCSD and founding director of the UC San Diego Center for Visual Computing. He earlier held tenured faculty positions at UC Berkeley and Columbia University, in all of which he played a key leadership role in building multi-faculty research groups recognized as leaders in computer vision and graphics. He has authored more than 200 refereed publications in computer graphics and vision, including 100+ ACM SIGGRAPH/TOG papers. He has consulted with Pixar and startups in computational imaging, and currently holds a part-time appointment as a Distinguished Research Scientist at NVIDIA. Prof. Ramamoorthi has received about twenty major honors including the ACM SIGGRAPH Significant New Researcher Award for his research in computer graphics, and the Presidential Early Career Award for Scientists and Engineers for his work on physics-based computer vision. He is a fellow of IEEE, ACM and the SIGGRAPH Academy, received two inaugural Frontiers of Science Awards, and has twice been honored with the edX Prize certificate for exceptional contributions in online teaching and learning. He has graduated more than 30 postdoctoral and Ph.D. students, whose theses have been recognized by the ACM Dissertation Award honorable mention, the SIGGRAPH outstanding dissertation award and the UCSD Chancellor’s Dissertation Medal.
Website: https://cseweb.ucsd.edu/~ravir/

Ravi Ramamoorthi : Sampling and Signal-Processing for High-Dimensional... : CMU Graphics Colloquium

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

array(10) { [0]=> object(stdClass)#4702 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "IpmxBMArfDU" ["related_video_title"]=> string(90) "🔴Jazz That Feels Like Time Travel – 1940s Calm Vibes | Music for Work & Study" ["posted_time"]=> string(0) "" ["channelName"]=> string(21) "The Jazz Time Machine" } [1]=> object(stdClass)#4675 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "3z4XlWHF1II" ["related_video_title"]=> string(72) "RI Seminar: Nikolai Matni : What Makes Learning to Control Easy or Hard?" ["posted_time"]=> string(27) "9 месяцев назад" ["channelName"]=> string(22) "CMU Robotics Institute" } [2]=> object(stdClass)#4700 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "U7dwzNMYO3w" ["related_video_title"]=> string(78) "RI Seminar: Sangbae Kim : Physical Intelligence and Cognitive Biases Toward AI" ["posted_time"]=> string(25) "2 месяца назад" ["channelName"]=> string(22) "CMU Robotics Institute" } [3]=> object(stdClass)#4707 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "PKixcYzo4fg" ["related_video_title"]=> string(84) "RI Seminar: Nikolay Atanasov : Learning Environment Models for Mobile Robot Autonomy" ["posted_time"]=> string(25) "2 месяца назад" ["channelName"]=> string(22) "CMU Robotics Institute" } [4]=> object(stdClass)#4686 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "2l-dv_z4KUc" ["related_video_title"]=> string(57) "Что полезного сделал ИИ? [Veritasium]" ["posted_time"]=> string(21) "6 дней назад" ["channelName"]=> string(10) "Vert Dider" } [5]=> object(stdClass)#4704 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "mtu64Y-oJyE" ["related_video_title"]=> string(79) "RMDO 2025: Shuran Song - Five Lessons Learned on Deformable Object Manipulation" ["posted_time"]=> string(25) "3 недели назад" ["channelName"]=> string(23) "ICRA 2025 RMDO Workshop" } [6]=> object(stdClass)#4699 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "blWdjRUPP6E" ["related_video_title"]=> string(72) "Разведчик о том, как использовать людей" ["posted_time"]=> string(25) "3 недели назад" ["channelName"]=> string(18) "Коллектив" } [7]=> object(stdClass)#4709 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "B1ULvYY-0Uo" ["related_video_title"]=> string(124) "Закон сохранения энергии — величайшее заблуждение физики [Veritasium]" ["posted_time"]=> string(19) "4 дня назад" ["channelName"]=> string(10) "Vert Dider" } [8]=> object(stdClass)#4685 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "qP4XEZ54eSc" ["related_video_title"]=> string(65) "Street Fighting Mathematics || @ CMU || Lecture 1c of TCS Toolkit" ["posted_time"]=> string(19) "5 лет назад" ["channelName"]=> string(14) "Ryan O'Donnell" } [9]=> object(stdClass)#4703 (5) { ["video_id"]=> int(9999999) ["related_video_id"]=> string(11) "Nc8Pxx24f-k" ["related_video_title"]=> string(120) "Аксиома выбора: как Георг Кантор чуть не сломал математику [Veritasium]" ["posted_time"]=> string(21) "8 дней назад" ["channelName"]=> string(10) "Vert Dider" } }

🔴Jazz That Feels Like Time Travel – 1940s Calm Vibes | Music for Work & Study

🔴Jazz That Feels Like Time Travel – 1940s Calm Vibes | Music for Work & Study

RI Seminar: Nikolai Matni : What Makes Learning to Control Easy or Hard?

RI Seminar: Nikolai Matni : What Makes Learning to Control Easy or Hard?

RI Seminar: Sangbae Kim : Physical Intelligence and Cognitive Biases Toward AI

RI Seminar: Sangbae Kim : Physical Intelligence and Cognitive Biases Toward AI

RI Seminar: Nikolay Atanasov : Learning Environment Models for Mobile Robot Autonomy

RI Seminar: Nikolay Atanasov : Learning Environment Models for Mobile Robot Autonomy

Что полезного сделал ИИ? [Veritasium]

Что полезного сделал ИИ? [Veritasium]

RMDO 2025: Shuran Song - Five Lessons Learned on Deformable Object Manipulation

RMDO 2025: Shuran Song - Five Lessons Learned on Deformable Object Manipulation

Разведчик о том, как использовать людей

Разведчик о том, как использовать людей

Закон сохранения энергии — величайшее заблуждение физики [Veritasium]

Закон сохранения энергии — величайшее заблуждение физики [Veritasium]

Street Fighting Mathematics || @ CMU || Lecture 1c of TCS Toolkit

Street Fighting Mathematics || @ CMU || Lecture 1c of TCS Toolkit

Аксиома выбора: как Георг Кантор чуть не сломал математику [Veritasium]

Аксиома выбора: как Георг Кантор чуть не сломал математику [Veritasium]