About
Former (2X) entrepreneur. Developed 3D and AI software for video games, security, smart cities, etc. Delivered mission-critical, real-time solutions. Refocused in 2017 on applying ML for 3D graphics and games.
Articles by Christian
Activity
-
Stable LM 2 12B released by Stability AI ! Proficient in 7 languages with good performance in several evaluation metrics. That's a cool-looking bear…
Stable LM 2 12B released by Stability AI ! Proficient in 7 languages with good performance in several evaluation metrics. That's a cool-looking bear…
Liked by Christian Laforte
-
Stable Audio 2.0 is out. A lot of hard work went into this from the Stable Audio team. I have really enjoyed working on this with Zach Evans…
Stable Audio 2.0 is out. A lot of hard work went into this from the Stable Audio team. I have really enjoyed working on this with Zach Evans…
Liked by Christian Laforte
-
Difference Between A Product Manager and A Project Manager! Free Product Management Courses🤗 1. Digital Product…
Difference Between A Product Manager and A Project Manager! Free Product Management Courses🤗 1. Digital Product…
Liked by Christian Laforte
Experience
-
Stability AI
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Education
-
3.2 GPA
-
-
Patents
-
Camera Projection Meshes
Issued Singapore 184509
Discloses highly-scalable 3D video fusion on commodity GPUs.
Filed in USA, Canada, Europe, Israel, India, Mexico, Singapore. As of April 20 2016, issued in Singapore and Mexico.
Abstract: A 3D rendering method is proposed to increase the performance when projecting and compositing multiple images or video sequences from real-world cameras on top of a precise 3D model of the real world. Unlike previous methods that relied on shadow- mapping and that were limited in performance due to…Discloses highly-scalable 3D video fusion on commodity GPUs.
Filed in USA, Canada, Europe, Israel, India, Mexico, Singapore. As of April 20 2016, issued in Singapore and Mexico.
Abstract: A 3D rendering method is proposed to increase the performance when projecting and compositing multiple images or video sequences from real-world cameras on top of a precise 3D model of the real world. Unlike previous methods that relied on shadow- mapping and that were limited in performance due to the need to re-render the complex scene multiple times per frame, the proposed method uses, for each camera, one Camera Projection Mesh ("CPM") of fixed and limited complexity per camera. The CPM that surrounds each camera is effectively molded over the surrounding 3D world surfaces or areas visible from the video camera. Rendering and compositing of the CPMs may be entirely performed on the Graphic Processing Unit ("GPU") using custom shaders for optimal performance. The method also enables improved view- shed analysis and fast visualization of the coverage of multiple cameras.
Other inventorsSee patent -
Effortless navigation across cameras and cooperative control of cameras
Issued Singapore 184520
- Automatic, optimal 3D camera selection, PTZ redirection
- Augmented reality applied to security
Filed in USA, Canada, Europe, Israel, India, Mexico, Singapore. As of April 20 2016, issued in Singapore and Mexico.
This application discloses a system and related methods (called Fast Track) to effortlessly navigate across multiple cameras, e.g. video surveillance cameras distributed in a facility. Fast Track simplifies the act of following a suspicious individual roaming in a…- Automatic, optimal 3D camera selection, PTZ redirection
- Augmented reality applied to security
Filed in USA, Canada, Europe, Israel, India, Mexico, Singapore. As of April 20 2016, issued in Singapore and Mexico.
This application discloses a system and related methods (called Fast Track) to effortlessly navigate across multiple cameras, e.g. video surveillance cameras distributed in a facility. Fast Track simplifies the act of following a suspicious individual roaming in a facility, e.g. by eliminating the need for security operators to memorize camera placement and coverage, and to manually control pan-tilt-zoom (hereinafter "PTZ") cameras, and by simplifying the process to reduce the risk of operator error. Combinations of novel scoring and control methods generally provide an automatic identification of optimal cameras and pre-emptive re-direction of PTZ cameras. Extensions to these methods enable two new capabilities: Cooperative PTZ Control (e.g. coordinating PTZs to cover a 3D map viewport optimally) and Self- Healing Perimeters, to automatically reassign and redirect multiple PTZ cameras to fill gaps in a security perimeter.
Other inventorsSee patent
Languages
-
English
Native or bilingual proficiency
-
French
Native or bilingual proficiency
-
Japanese
Professional working proficiency
Recommendations received
6 people have recommended Christian Join now to view
More activity by Christian
SD3 already in Turbo. Thanks for posting Ahsen Khaliq https://lnkd.in/gX_iv4b9
Liked by Christian Laforte
Likewise! I'm honoured that we were chosen as Interim Co-CEOs to lead Stability AI by Emad Mostaque (original CEO) and our Board of Directors. We…
Shared by Christian Laforte
It is a privilege to be leading Stability AI alongside Christian Laforte as Interim Co-CEO into its next phase of growth http://bit.ly/43zsVjN
Liked by Christian Laforte
Stability AI is supporting the AI ecosystem in Japan. In collaboration with AWS and Anobaka, here is an event about AI trends and the startup…
Liked by Christian Laforte
In this installment of "Behind the Compute", a series dedicated to offering insights for others to harness the power of generative AI, we compared…
Liked by Christian Laforte
Robin's team just published the Stable Diffusion 3 paper - a huge leap forward. It beats all the competitors and we're working hard to release it…
Shared by Christian Laforte
We just released (jointly with a research partner called Tripo AI) the TripoSR image-to-3D model. With it, you can get a 3D model in 0.5s.
Shared by Christian Laforte
Come work with Stephen Neuendorffer !! Our SHARK team works closely with Stephen and leverages all of the core work his team has done with #MLIR…
Liked by Christian Laforte
People also viewed
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 More