From Concept to Reality: The Journey of Building Scaniverse

Computer Vision Decoded

#Science #Tech #Jonathan Stephens #Computer Vision #Machine Learning #Apple #Photogrammetry #Spatial Computing

33:19

What’s the secret to lasting friendships? How does queer community show up through the ebbs and flows of life? And what’s the REAL story behind the “YMCA” song? In the first episode of Silver Linings, The Old Gays dive into an essential part of queer life: chosen family. They discuss the vital love, support, and sense of belonging that community provides, especially during life's toughest moments. They open up about what “queer” means to them, how chosen family has impacted their lives, and how to maintain close bonds over time–including their love for each other! “We’ve come a long way, baby.” Family isn’t just what you’re born with; it’s the people who show up, shape you, and stick around. See omnystudio.com/listener for privacy information.…

2 years ago 50:05

MP3•Episode home

In this episode, we discuss…

01:00 - Keith's Ito's background at Google
09:44 - What is the Scaniverse app
11:43 - What inspired Keith to build Scaniverse
17:37 - The challenges of using LiDAR in the early versions of Scaniverse
25:54 - How to build a good user experience for 3D capture apps
32:00 - The challenges of running photogrammetry on an iPhone
37:07 - The future of 3D capture
40:57 - Scaniverse's role at Niantic

Learn more about Scaniverse at: https://scaniverse.com/
Follow Keith Ito on Twitter at: https://twitter.com/keeeto

Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly
Follow Jonathan Stephens on Twitter: https://twitter.com/jonstephens85
Follow Jonathan Stephens on LinkedIn: https://www.linkedin.com/in/jonathanstephens/

-----

This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io

16 episodes

From Concept to Reality: The Journey of Building Scaniverse

Computer Vision Decoded

0-10 subscribers

published 2 years ago

MP3•Episode home

In this episode, we discuss…

01:00 - Keith's Ito's background at Google
09:44 - What is the Scaniverse app
11:43 - What inspired Keith to build Scaniverse
17:37 - The challenges of using LiDAR in the early versions of Scaniverse
25:54 - How to build a good user experience for 3D capture apps
32:00 - The challenges of running photogrammetry on an iPhone
37:07 - The future of 3D capture
40:57 - Scaniverse's role at Niantic

Learn more about Scaniverse at: https://scaniverse.com/
Follow Keith Ito on Twitter at: https://twitter.com/keeeto

-----

16 episodes

#Science #Tech #Jonathan Stephens #Computer Vision #Machine Learning #Apple #Photogrammetry #Spatial Computing

All episodes

Computer Vision Decoded

1
Camera Types for 3D Reconstruction Explained 1:15:35

21 days ago1:15:35

1:15:35

In this episode of Computer Vision Decoded, hosts Jonathan Stephens and Jared Heinly explore the various types of cameras used in computer vision and 3D reconstruction. They discuss the strengths and weaknesses of smartphone cameras, DSLR and mirrorless cameras, action cameras, drones, and specialized cameras like 360, thermal, and event cameras. The conversation emphasizes the importance of understanding camera specifications, metadata, and the impact of different lenses on image quality. The hosts also provide practical advice for beginners in 3D reconstruction, encouraging them to start with the cameras they already own. Takeaways Smartphones are versatile and user-friendly for photography. RAW images preserve more data than JPEGs, aiding in post-processing. Mirrorless and DSLR cameras offer better low-light performance and lens flexibility. Drones provide unique perspectives and programmable flight paths for capturing images. 360 cameras allow for quick scene capture but may require additional processing for 3D reconstruction. Event cameras capture rapid changes in intensity, useful for robotics applications. Thermal and multispectral cameras are specialized for specific applications, not typically used for 3D reconstruction. Understanding camera metadata is crucial for effective image processing. Choosing the right camera depends on the specific needs of the project. Starting with a smartphone is a low barrier to entry for beginners in 3D reconstruction. This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
Understanding 3D Reconstruction with COLMAP 57:02

9 weeks ago57:02

57:02

In this episode, Jonathan Stephens and Jared Heinly delve into the intricacies of COLMAP, a powerful tool for 3D reconstruction from images. They discuss the workflow of COLMAP, including feature extraction, correspondence search, incremental reconstruction, and the importance of camera models. The conversation also covers advanced topics like geometric verification, bundle adjustment, and the newer GLOMAP method, which offers a faster alternative to traditional reconstruction techniques. Listeners are encouraged to experiment with COLMAP and learn through hands-on experience. This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
Tips and Tricks for 3D Reconstruction in Different Environments 1:21:23

13 weeks ago1:21:23

1:21:23

In this episode, we discuss practical tips and challenges in 3D reconstruction from images, focusing on various environments such as urban, indoor, and outdoor settings. We explore issues like repetitive structures, lighting conditions, and the impact of reflections and shadows on reconstruction quality. The conversation also touches on the importance of camera motion, lens distortion, and the role of machine learning in enhancing reconstruction processes. Listeners gain insights into optimizing their 3D capture techniques for better results. Key Takeaways Repetitive structures can confuse computer vision algorithms. Lighting conditions greatly affect image quality and reconstruction accuracy. Wide-angle lenses can help capture more unique features. Indoor environments present unique challenges like textureless walls. Aerial imaging requires careful management of lens distortion. Understanding the application context is crucial for effective 3D reconstruction. Camera motion should be varied to avoid distortion and drift. Planning captures based on goals can lead to better results. This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services. Learn more at https://www.everypoint.io…

Computer Vision Decoded

1
Exploring Depth Maps in Computer Vision 57:31

15 weeks ago57:31

57:31

In this episode of Computer Vision Decoded, Jonathan Stephens and Jared Heinly explore the concept of depth maps in computer vision. They discuss the basics of depth and depth maps, their applications in smartphones, and the various types of depth maps. The conversation delves into the role of depth maps in photogrammetry and 3D reconstruction, as well as future trends in depth sensing and machine learning. The episode highlights the importance of depth maps in enhancing photography, gaming, and autonomous systems. Key Takeaways: Depth maps represent how far away objects are from a sensor. Smartphones use depth maps for features like portrait mode. There are multiple types of depth maps, including absolute and relative. Depth maps are essential in photogrammetry for creating 3D models. Machine learning is increasingly used for depth estimation. Depth maps can be generated from various sensors, including LiDAR. The resolution and baseline of cameras affect depth perception. Depth maps are used in gaming for rendering and performance optimization. Sensor fusion combines data from multiple sources for better accuracy. The future of depth sensing will likely involve more machine learning applications. Episode Chapters 00:00 Introduction to Depth Maps 00:13 Understanding Depth in Computer Vision 06:52 Applications of Depth Maps in Photography 07:53 Types of Depth Maps Created by Smartphones 08:31 Depth Measurement Techniques 16:00 Machine Learning and Depth Estimation 19:18 Absolute vs Relative Depth Maps 23:14 Disparity Maps and Depth Ordering 26:53 Depth Maps in Graphics and Gaming 31:24 Depth Maps in Photogrammetry 34:12 Utilizing Depth Maps in 3D Reconstruction 37:51 Sensor Fusion and SLAM Technologies 41:31 Future Trends in Depth Sensing 46:37 Innovations in Computational Photography This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services. Learn more at https://www.everypoint.io…

Computer Vision Decoded

1
What's New in 2025 for Computer Vision? 50:03

16 weeks ago50:03

50:03

After an 18 month hiatus, we are back! In this episode of Computer Vision Decoded, hosts Jonathan Stephens and Jared Heinly discuss the latest advancements in computer vision technology, personal updates, and insights from the industry. They explore topics such as real-time 3D reconstruction, computer vision research, SLAM, event cameras, and the impact of generative AI on robotics. The conversation highlights the importance of merging traditional techniques with modern machine learning approaches to solve real-world problems effectively. Chapters 00:00 Intro & Personal Updates 04:36 Real-Time 3D Reconstruction on iPhones 09:40 Advancements in SfM 14:56 Event Cameras 17:39 Neural Networks in 3D Reconstruction 26:30 SLAM and Machine Learning Innovation 29:48 Applications of SLAM in Robotics 34:19 NVIDIA's Cosmos and Physical AI 40:18 Generative AI for Real-World Applications 43:50 The Future of Gaussian Splatting and 3D Reconstruction This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
A Computer Vision Scientist Reacts to the iPhone 15 Announcement 42:17

2 years ago42:17

42:17

In this episode of Computer Vision Decoded, we are going to dive into our in-house computer vision expert's reaction to the iPhone 15 and iPhone 15 Pro announcement. We dive into the camera upgrades, decode what a quad sensor means, and even talk about the importance of depth maps. Episode timeline: 00:00 Intro 02:59 iPhone 15 Overview 05:15 iPhone 15 Main Camera 07:20 Quad Pixel Sensor Explained 15:45 Depth Maps Explained 22:57 iPhone 15 Pro Overview 27:01 iPhone 15 Pro Cameras 32:20 Spatial Video 36:00 A17 Pro Chipset This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
OpenMVG Decoded: Pierre Moulon's 10 Year Journey Building Open-Source Software 55:44

2 years ago55:44

55:44

In this episode of Computer Vision Decoded, we are going to dive into Pierre Moulon's 10 years experience building OpenMVG. We also cover the impact of open-source software in the computer vision industry and everything involved in building your own project. There is a lot to learn here! Our episode guest, Pierre Moulon, is a computer vision research scientist and creator of OpenMVG - a library for computer-vision scientists and targeted for the Multiple View Geometry community. The episode follow's Pierre's journey building OpenMVG which he wrote about as an article in his GitHub repository. Explore OpenMVG on GitHub: https://github.com/openMVG/openMVG Pierre's article on building OpenMVG: https://github.com/openMVG/openMVG/discussions/2165 Episode timeline: 00:00 Intro 01:00 Pierre Moulon's Background 04:40 What is OpenMVG? 08:43 What is the importance of open-source software for the computer vision community? 12:30 What to look for deciding to use an opensource project 16:27 What is Multi View Geometry? 24:24 What was the biggest challenge building OpenMVG? 31:00 How do you grow a community around an open-source project 38:09 Choosing a licensing model for your open-source project 43:07 Funding and sponsorship for your open-source project 46:46 Building an open-source project for your resume 49:53 How to get started with OpenMVG Contact: Follow Pierre Moulon on LinkedIn: https://www.linkedin.com/in/pierre-moulon/ Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly Follow Jonathan Stephens on Twitter at: https://twitter.com/jonstephens85 This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
Understanding Implicit Neural Representations with Itzik Ben-Shabat 55:22

2 years ago55:22

55:22

In this episode of Computer Vision Decoded, we are going to dive into implicit neural representations. We are joined by Itzik Ben-Shabat, a Visiting Research Fellow at the Australian National Universit (ANU) and Technion – Israel Institute of Technology as well as the host of the Talking Paper Podcast . You will learn a core understanding of implicit neural representations, key concepts and terminology, how it's being used in applications today, and Itzik's research into improving output with limit input data. Episode timeline: 00:00 Intro 01:23 Overview of what implicit neural representations are 04:08 How INR compares and contrasts with a NeRF 08:17 Why did Itzik pursued this line of research 10:56 What is normalization and what are normals 13:13 Past research people should read to learn about the basics of INR 16:10 What is an implicit representation (without the neural network) 24:27 What is DiGS and what problem with INR does it solve? 35:54 What is OG-I NR and what problem with INR does it solve? 40:43 What software can researchers use to understand INR? 49:15 What information should non-scientists be focused to learn about INR? Itzik's Website: https://www.itzikbs.com/ Follow Itzik on Twitter: https://twitter.com/sitzikbs Follow Itzik on LinkedIn: https://www.linkedin.com/in/yizhak-itzik-ben-shabat-67b3b1b7/ Talking Papers Podcast: https://talking.papers.podcast.itzikbs.com/ Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly Follow Jonathan Stephens on Twitter at: https://twitter.com/jonstephens85 Referenced past episode- What is CVPR: https://share.transistor.fm/s/15edb19d This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
From 2D to 3D: 4 Ways to Make a 3D Reconstruction from Imagery 54:29

2 years ago54:29

54:29

In this episode of Computer Vision Decoded, we are going to dive into 4 different ways to 3D reconstruct a scene with images. Our cohost Jared Heinly, a PhD in the computer science specializing in 3D reconstruction from images, will dive into the 4 distinct strategies and discuss the pros and cons of each. Links to content shared in this episode: Live SLAM to measure a stockpile with SR Measure: https://srmeasure.com/professional Jared's notes on the iPhone LiDAR and SLAM: https://everypoint.medium.com/everypoint-gets-hands-on-with-apples-new-lidar-sensor-44eeb38db579 How to capture images for 3D reconstruction: https://youtu.be/AQfRdr_gZ8g 00:00 Intro 01:30 3D Reconstruction from Video 13:48 3D Reconstruction from Images 28:05 3D Reconstruction from Stereo Pairs 38:43 3D Reconstruction from SLAM Follow Jared Heinly Twitter: https://twitter.com/JaredHeinly LinkedIn https://www.linkedin.com/in/jheinly/ Follow Jonathan Stephens Twitter: https://twitter.com/jonstephens85 LinkedIn: https://www.linkedin.com/in/jonathanstephens/ This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
From Concept to Reality: The Journey of Building Scaniverse 50:05

2 years ago50:05

50:05

Join our guest, Keith Ito, founder of Scaniverse as we discuss the challenges of creating a 3D capture app for iPhones. Keith goes into depth on balancing speed with quality of 3D output and how he designed an intuitive user experience for his users. In this episode, we discuss… 01:00 - Keith's Ito's background at Google 09:44 - What is the Scaniverse app 11:43 - What inspired Keith to build Scaniverse 17:37 - The challenges of using LiDAR in the early versions of Scaniverse 25:54 - How to build a good user experience for 3D capture apps 32:00 - The challenges of running photogrammetry on an iPhone 37:07 - The future of 3D capture 40:57 - Scaniverse's role at Niantic Learn more about Scaniverse at: https://scaniverse.com/ Follow Keith Ito on Twitter at: https://twitter.com/keeeto Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly Follow Jonathan Stephens on Twitter: https://twitter.com/jonstephens85 Follow Jonathan Stephens on LinkedIn: https://www.linkedin.com/in/jonathanstephens/ ----- This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
Will NeRFs Replace Photogrammetry? 52:14

3 years ago52:14

52:14

In this episode of Computer Vision Decoded, we are going to dive into one of the hottest topics in the industry: Neural Radiance Fields (NeRFs) We are joined by Matt Tancik, a student pursuing a PhD in the computer science and electrical engineering department at UC Berkeley. He has also contributed research to the original NeRF project in 2020 along with several others since then. Last but not least, he is building NeRFStudio - a collaboration friendly studio for NeRFs. In this episode you will learn about what NeRFs are and more importantly what they are not. Matt goes into the challenges of large scale NeRF creation with his experience with Block-NeRF. Follow Matt's work at https://www.matthewtancik.com/ Get started with Nerfstudio here: https://docs.nerf.studio/en/latest/ Block-NeRF details: https://waymo.com/research/block-nerf/ 00:00 Intro 00:45 Matt’s Background Into NeRF Research 04:00 What is a NeRF and how it is different from photogrammetry 11:57 Can geometry be extracted from NeRFs? 15:30 Will NeRFs supersede photogrammetry in the future? 22:47 Block-NeRF and the pros and cons of using 360 cameras 25:30 What is the goal of Block-NeRF 30:44 Why do NeRFs need large GPUs to compute? 35:45 Meshes to simulate NeRF visualizations 40:28 What is Nerfstudio? 47:40 How to get started with Nerfstudio Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly Follow Jonathan Stephens on Twitter at: https://twitter.com/jonstephens85 This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
How to Capture Images for 3D Reconstruction 1:23:29

3 years ago1:23:29

1:23:29

In this episode of Computer Vision Decoded, we are going to dive into image capture best practices for 3D reconstruction. At the end of this livestream, you will have learned the basics for capturing scenes and objects. We will also provide a downloadable visual guide for reference on your next 3D reconstruction project. Download the official guide here to follow along: https://tinyurl.com/4n2wspkn 00:00 Intro 04:40 Camera motion overview 07:15 Good camera motions 18:43 Transition camera motions 30:39 Bad camera motions 39:27 How to combine camera motions 49:16 Loop Closure 57:42 Image Overlap 1:14:00 Lighting and camera gear Watch out episode of Computer Vision in the Wild to learn more about capturing images outside and in busy locations: https://youtu.be/FwVBR6KFjPI Follow Jared Heinly on Twitter: https://twitter.com/JaredHeinly Follow Jonathan Stephens on Twitter at: https://twitter.com/jonstephens85 This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
Is The iPhone 14 Camera Any Good? 1:01:34

3 years ago1:01:34

1:01:34

In this episode of Computer Vision Decoded, we join Jared Heinly and Jonathan Stephens from EveryPoint for their live reaction to the iPhone 14 series announcement. They go in depth into what all the camera specs mean to the average person. We also explain basics of computational photography and how Apple is able to get great photos from a small camera sensor. 00:00 Intro 02:43 Apple Watch Review 06:58 Airpods Pro Review 09:40 iPhone 14 Initial Reaction 15:05 iPhone 14 Camera Specs Breakdown 37:13 iPhone 14 Pro Initial Reaction 40:47 iPhone 14 Pro Camera Specs Breakdown Follow Jared Heinly on Twitter Follow Jonathan Stephens on Twitter This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
3D Reconstruction in the Wild 1:01:51

3 years ago1:01:51

1:01:51

In this episode of Computer Vision Decoded, we sit down with Jared Heinly, Chief Scientist at EveryPoint, to discuss 3D reconstruction in the wild. What does “in the wild” mean? This means 3D reconstructing objects and scenes in non-controlled environments where you may have limitations with lighting, access, reflective surfaces, etc. 00:00 Intro 01:30: What are Duplicate Scene Structures and How to Avoid Them 14:30: How Jared used 100 million crowdsourced photos to 3d reconstruct 12,903 landmarks 27:10: The benefits of capturing video for 3D reconstruction 31:30: The benefits of using a drone to capture stills for 3D reconstruction 34:20: Considerations for using installed cameras for 3d reconstruction 38:30: How to work with sun issues 44:25: Determining how far from the object you should be when capturing images 50:35: How to capture objects with reflective surfaces 53:40: How work around scene obstructions 57:20: What cameras you should use Jared Heinly’s Academic Papers and Projects Paper: Correcting the Duplicate Scene Structure In Sparse 3D Reconstruction Project: Reconstructing the World in Six Days Video: Reconstructing the world in Six Days Follow Jared Heinly on Twitter Follow Jonathan Stephens on Twitter This episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io…

Computer Vision Decoded

1
What is the CVPR Conference? 29:17

3 years ago29:17