About
Contributions
-
Here's how you can effectively communicate with your boss about your career progression.
1. Write down our goals. 2. Check in regularly to ensure alignment (business and personal growth). 3. Take action! You and your manager can win if you can see the end goals. Remember it is a long journey and a rough ride =) Take it easy.
Activity
-
Building Agentic RAG - Llama3 edition 🦙💫 We’re excited to collaborate with some folks at AI at Meta to release an entire set of cookbooks on…
Building Agentic RAG - Llama3 edition 🦙💫 We’re excited to collaborate with some folks at AI at Meta to release an entire set of cookbooks on…
Liked by Raymond Lo 👓🤖
-
I’m thrilled to see our Intel Software Innovator from France, Arnaud Bastide joining forces with the Intel Evangelism Team- Dmitriy Pastushenkov and…
I’m thrilled to see our Intel Software Innovator from France, Arnaud Bastide joining forces with the Intel Evangelism Team- Dmitriy Pastushenkov and…
Liked by Raymond Lo 👓🤖
-
Hot off the press - Computer Vision News of July 2024 Here is the BEST OF CVPR. You will read full reviews of the winning Best Paper, two candidate…
Hot off the press - Computer Vision News of July 2024 Here is the BEST OF CVPR. You will read full reviews of the winning Best Paper, two candidate…
Liked by Raymond Lo 👓🤖
Experience & Education
Publications
-
Connecting the Real-World and Metaverse via Real-Time Digitization with Intel Arc Graphics
SIGGRAPH ASIA 2022
The automation process of connecting the real-world is one of the key building blocks for creating a truly immersive metaverse. With the advance of deep learning techniques, we could expect that in future of AR/VR, OCR along with natural language processing (NLP), could help us to digitize, structure or translate all text information according to our needs, from different sources to every AR, VR or mobile wearable device. With the mapping of real-world information to the virtual world, existing…
The automation process of connecting the real-world is one of the key building blocks for creating a truly immersive metaverse. With the advance of deep learning techniques, we could expect that in future of AR/VR, OCR along with natural language processing (NLP), could help us to digitize, structure or translate all text information according to our needs, from different sources to every AR, VR or mobile wearable device. With the mapping of real-world information to the virtual world, existing or historical knowledge could be best utilized to generate more creative and resourceful results for a more splendid metaverse.
Optical character recognition (OCR) is one of the earliest addressed computer vision tasks, for which different implementations have been proposed. Although in some specific use cases, certain OCR implementations yield very-good results, up to 99% accuracy, a general OCR that could provide high accuracy in different text density, structures of text, fonts, artifacts or text locations is still quite challenging. Therefore, deep-learning based OCR implementation has been widely investigated in recent years, given its strong learning abilities and high robustness. In this hands-on course, what we are learning is 1) a working pipeline to perform automatic digitization based on OCR and NLP algorithms, for uploaded images or through an AR demo; 2) a step-by-step tutorial on how to use OpenVINO to accelerate the inference for OCR and NLP; 3) evaluation and deployment of the solution as an edge-computing system with plain CPU.Other authorsSee publication -
CVPR 2022 Tutorial - How to get quick and performant model for your edge application. From data to application
CVPR
https://paularamo.github.io/cvpr-2022/
How to get quick and performant model for your edge application. From data to application.
Organizers:
Paula Ramos, Raymond Lo, Helena Kloosterman, Samet Akcay, Zhuo Wu & Yury GorbachevOther authorsSee publication -
Embodied Humanistic Intelligence: Design of Augmediated Reality Digital Eye Glass
University of Toronto
In this thesis, I present a new generation of Augmediated Reality Digital Eye Glass (DEG) that embodies the principles of Humanistic Intelligence (HI). In particular, this thesis addresses the fundamental issues in the practical realization of the HI framework, most notably the dynamic range of sensors and the design of a natural human-computer interface based on three dimensional (3D) gestural input. First, to address the dynamic range limitation of color sensors, a practical implementation of…
In this thesis, I present a new generation of Augmediated Reality Digital Eye Glass (DEG) that embodies the principles of Humanistic Intelligence (HI). In particular, this thesis addresses the fundamental issues in the practical realization of the HI framework, most notably the dynamic range of sensors and the design of a natural human-computer interface based on three dimensional (3D) gestural input. First, to address the dynamic range limitation of color sensors, a practical implementation of high dynamic range (HDR) image composition and tone mapping algorithms were designed on both Field-programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs) to enable real-time processing of video streams. The algorithms are optimized for wearable applications and provide a constant runtime performance independent of the scene. To demonstrate the robustness of the algorithm, a specialized DEG helmet was designed to work under the most extreme lighting condition - tungsten inert gas welding. In addition, I discuss the development of a novel HDR technique for 3D depth sensing cameras called 3DHDR. Here, I present a method of creating 3D HDR depth maps using an array of 3D depth sensing cameras designed for wearable applications. The system provides a tonal and spatial range that significantly exceeds the capability of any individual depth sensor. Finally, I present an untethered wearable solution of DEG with 3D gestural input based on 3DHDR. The recognition system provides various mode of operations and allows users to integrate gesture-based input to control the Augmediated Reality DEG system. The final prototype has been translated to a development platform for use in future wearable computing research to further explore the HI framework.
-
Immersive augmented reality in Minutes with Meta 2
SIGGRAPH '16: ACM SIGGRAPH 2016 Real-Time Live!
Overlaying and registering interactive virtual content on the real world requires sophisticated hardware and advanced software: cutting-edge optics, state-of-the-art sensors, and the latest in computer vision and computer graphics algorithms. Meta 2 provides an easy-to-use platform for creating augmented reality applications that abstracts these complexities.
-
OpenGL Data Visualization Cookbook
Packt Publishing
OpenGL is a great multi-platform, cross-language, and hardware-accelerated graphics interface for visualizing large 2D and 3D datasets. Data visualization has become increasingly challenging using conventional approaches as datasets become larger and larger, especially with the Big Data evolution. From a mobile device to a sophisticated high-performance computing cluster, OpenGL libraries provide developers with an easy-to-use interface to create stunning visuals in 3D in real time for…
OpenGL is a great multi-platform, cross-language, and hardware-accelerated graphics interface for visualizing large 2D and 3D datasets. Data visualization has become increasingly challenging using conventional approaches as datasets become larger and larger, especially with the Big Data evolution. From a mobile device to a sophisticated high-performance computing cluster, OpenGL libraries provide developers with an easy-to-use interface to create stunning visuals in 3D in real time for a wide range of interactive applications.
This book provides an easy-to-follow, hands-on tutorials to create appealing OpenGL-based visualization tools with minimal development time. We will first illustrate how to quickly set up the development environment in Windows, Mac, and Linux. Next, we will demonstrate how to visualize data for a wide range of applications using OpenGL, starting from simple 2D datasets to increasingly complex 3D datasets with more advanced techniques. Each chapter addresses different visualization problems encountered in real life and introduces the relevant OpenGL features and libraries in a modular fashion. By the end of this book, you will be equipped with the essential skills to develop a wide range of impressive OpenGL-based applications for your unique data visualization needs, on platforms ranging from conventional computers to the latest mobile/wearable devices.
Patents
-
Apparatuses, methods and systems coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest
Issued US 20160260258
Aspects of the disclosed apparatuses, methods and systems provide three dimensional gradient and dynamic light fields for display in 3D technologies, in particular 3D augmented reality (AR) devices, by coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest in real time.
Other inventorsSee patent -
Apparatuses, methods and systems coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest
Issued US 9576399
Aspects of the disclosed apparatuses, methods and systems provide three dimensional gradient and dynamic light fields for display in 3D technologies, in particular 3D augmented reality (AR) devices, by coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest in real time.
-
Head-mounted display
Issued US D776110
-
APPARATUSES, METHODS AND SYSTEMS FOR PRE-WARPING IMAGES FOR A DISPLAY SYSTEM WITH A DISTORTING OPTICAL COMPONENT
Filed US 20170193687
Aspects of the disclosed apparatuses, methods and systems provide elimination of distortion induced by an optical system that reflects light from an image source. An inverse mapping of the distortion is created for the optical system. The display system applies the inverse mapping to an image prior to display to introduce a distortion to the displayed image that is the inverse of the distortion introduced by the optical system. As a result, the distortion in the displayed image is canceled by…
Aspects of the disclosed apparatuses, methods and systems provide elimination of distortion induced by an optical system that reflects light from an image source. An inverse mapping of the distortion is created for the optical system. The display system applies the inverse mapping to an image prior to display to introduce a distortion to the displayed image that is the inverse of the distortion introduced by the optical system. As a result, the distortion in the displayed image is canceled by the distortion of the optical element providing the user with an image that is substantially distortion free.
-
APPARATUSES, METHODS AND SYSTEMS FOR APPLICATION OF FORCES WITHIN A 3D VIRTUAL ENVIRONMENT
Filed US 20170193706
Aspects of the disclosed apparatuses, methods and systems provide manipulation of a virtual world three dimensional (3D) space based on input translated from the real world. Elements in the virtual world may have an associated charge and field. An element in the virtual world becomes interactive with an element translated from the real world when the translated real world element interacts with a field associated with the virtual element according to the charges. Forces may be applied to the…
Aspects of the disclosed apparatuses, methods and systems provide manipulation of a virtual world three dimensional (3D) space based on input translated from the real world. Elements in the virtual world may have an associated charge and field. An element in the virtual world becomes interactive with an element translated from the real world when the translated real world element interacts with a field associated with the virtual element according to the charges. Forces may be applied to the virtual element using a real world physics model to determine a response by the virtual element to the applied force.
-
Apparatuses, methods and systems coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest
Issued US 20160260258
Aspects of the disclosed apparatuses, methods and systems provide three dimensional gradient and dynamic light fields for display in 3D technologies, in particular 3D augmented reality (AR) devices, by coupling visual accommodation and visual convergence to the same plane at any depth of an object of interest in real time.
-
OPTICAL ENGINE FOR CREATING WIDE-FIELD OF VIEW FOVEA-BASED DISPLAY
Filed US 20170188021
Methods, systems, components, and techniques provide a retinal light scanning engine to write light corresponding to an image on the retina of a viewer. As described herein, a light source of the retinal light scanning engine forms a single point of light on the retina at any single, discrete moment in time. In one example, to form a complete image, the retinal light scanning engine uses a pattern to scan or write on the retina to provide light to millions of such points over one time segment…
Methods, systems, components, and techniques provide a retinal light scanning engine to write light corresponding to an image on the retina of a viewer. As described herein, a light source of the retinal light scanning engine forms a single point of light on the retina at any single, discrete moment in time. In one example, to form a complete image, the retinal light scanning engine uses a pattern to scan or write on the retina to provide light to millions of such points over one time segment corresponding to the image. The retinal light scanning engine changes the intensity and color of the points drawn by the pattern by simultaneously controlling the power of different light sources and movement of an optical scanner to display the desired content on the retina according to the pattern. In addition, the pattern may be optimized for writing an image on the retina. Moreover, multiple patterns may be used to additional increase or improve the field-of-view of the display.
-
System and method for providing views of virtual content in an augmented reality environment
Filed US 9773438
A system configured for providing views of virtual content in an augmented reality environment may comprise one or more of a first display, a second display, an optical element, one or more processors, and/or other components. The first display and second display may be separated by a separation distance. The first display and second display may be arranged such that rays of light emitted from pixels of the first display may travel through the second display, then reflect off the optical…
A system configured for providing views of virtual content in an augmented reality environment may comprise one or more of a first display, a second display, an optical element, one or more processors, and/or other components. The first display and second display may be separated by a separation distance. The first display and second display may be arranged such that rays of light emitted from pixels of the first display may travel through the second display, then reflect off the optical element and into a user's eyes. A three-dimensional light field perceived with a user's field-of-view may be generated. Distances of the first display and/or second display to the optical element may impact a perceived range of the three-dimensional light field. The separation distance may impact a perceived depth of the three-dimensional light field and/or a resolution of virtual content perceived with the three-dimensional light field.
Projects
-
TED 2016
Constructed the on stage demo, and teleport in front of hundreds of audience in real-time. Also, we lead 400+ demos sessions during the conference.
Honors & Awards
-
SIGGRAPH 2016 Best of the Show
Computer Graphics World
http://www.cgw.com/Press-Center/News/2016/Computer-Graphics-World-Selects-SIGGRAPH-2016-Be.aspx
Languages
-
English
Native or bilingual proficiency
More activity by Raymond
-
90% of the time, when I speak with an AI Product Manager or a ML engineer, they do not know this gold mine of production-grade AI models. I am…
90% of the time, when I speak with an AI Product Manager or a ML engineer, they do not know this gold mine of production-grade AI models. I am…
Liked by Raymond Lo 👓🤖
-
🎉 Google's Gemini AI integration with Colab comes pretty handy at times. For instance, I wanted to lookup the documentation of "pandas.factorize"…
🎉 Google's Gemini AI integration with Colab comes pretty handy at times. For instance, I wanted to lookup the documentation of "pandas.factorize"…
Liked by Raymond Lo 👓🤖
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Raymond Lo 👓🤖 in United States
-
Raymond Lo
Sales Manager at Mercedes Benz of Henderson
-
Raymond Lo
Name Creation & Regulatory Strategy at Novartis
-
Raymond Lo
-
Raymond Lo
Consulting Manager at DB E.C.O. North America Inc.
75 others named Raymond Lo 👓🤖 in United States are on LinkedIn
See others named Raymond Lo 👓🤖