New SOTA Depth Estimation Model with a Monocular Camera
ฝัง
- เผยแพร่เมื่อ 4 ก.ค. 2024
- Inside my school and programs, I teach you my system to become an AI engineer or freelancer. Life-time access and help by me and I will show you exactly how I went from below average student to making $250/hr. I also have a ton of technical courses. Join the High Earner AI Career Program here 👉 www.nicolai-nielsen.com/aicareer (LIMITED EARLY-BIRD OFFER, PRICES WILL INCREASE SOON)
In this video 📝 we are going to take a look at some of the new SOTA depth estimation models with a monocular camera. We will go over the results and how the models work. Then I'll show you have to set it up so you can use it in your own applications and projects.
If you enjoyed this video, be sure to press the 👍 button so that I know what content you guys like to see.
_______________________________________________________________
Freelance Work: www.nicolai-nielsen.com/nncode
_______________________________________________________________
📞 Connect with Me:
🌳 linktr.ee/nicolainielsen
🌍 My Website: www.nicolai-nielsen.com/
🤖 GitHub: github.com/niconielsen32
👉 LinkedIn: / nicolaiai
🐦 Twitter: / nielsencv_ai
🌆 Instagram: / nicolaihoeirup
_______________________________________________________________
🎮 My Gear (Affiliate links):
💻 Laptop: amzn.to/49LJkTW
🖥️ Desktop:
NVIDIA RTX 4090 24GB: amzn.to/3Uc7yAM
Intel I9-14900K: amzn.to/3W4Z5Cb
Motherboard: amzn.to/4aR6wBC
32GB RAM: amzn.to/3Jt2XVR
🖥️ Monitor: amzn.to/4aLP8hh
🖱️ Mouse: amzn.to/3W501GH
⌨️ Keyboard: amzn.to/3xUGz5b
🎙️ Microphone: amzn.to/3w1F1WK
📷 Camera: amzn.to/4b4Ryr9
_______________________________________________________________
Timestamps:
0:00 Intro
1:00 Zero-Shot
2:45 Marigold Project Website
6:29 Marigold Huggingface
8:05 Marigold Local Setup
15:25 Marigold Reults
16:48 Outro
tags:
#Depthmap #DepthEstimation #Marigold #Zero-Shot - วิทยาศาสตร์และเทคโนโลยี
Join My AI Career Program
👉 www.nicolai-nielsen.com/aicareer
Enroll in My School and Technical Courses
👉 www.nicos-school.com
In monocular depth estimation models, usually so-called "relative depth" is predicted, but in application, how should I recover real metric depth from the prediction? Perhaps make sort of calibration?
thanks for the video, im working with depth estimation on my masters
Awesome man! Hope you can get some inspiration. Good luck with your masters!
already watched your previous video about 3d estimation,this result with cat face was guite incredible!can't wait to see AI features with that
Yeah a lot of cool things for sure and so much is happening! A bit unfortunate that google deepmind hasn't released the code for theirs.
Thank you for sharing, I really enjoy your videos. In your opinion, which method is better, this one or Depth anything? Could you evaluate both in terms of accuracy and speed?
Thanks a ton! Accuracy Might be slightly better on this one but depth anything is Way Way faster and still awesome performance. Would use depth anything in every situation
I totally agree with you, and the network structure of Depth anything is more straightforward and intuitive. Their paper also mentions that their goal is to achieve good results with a simple network architecture.@@NicolaiAI