Рет қаралды 34,377
❤️ Support the channel ❤️
/ @aladdinpersson
Paper: arxiv.org/abs/2003.08934
Full title: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Paid Courses I recommend for learning (affiliate links, no extra cost for you):
⭐ Machine Learning Specialization bit.ly/3hjTBBt
⭐ Deep Learning Specialization bit.ly/3YcUkoI
📘 MLOps Specialization bit.ly/3wibaWy
📘 GAN Specialization bit.ly/3FmnZDl
📘 NLP Specialization bit.ly/3GXoQuP
✨ Free Resources that are great:
NLP: web.stanford.edu/class/cs224n/
CV: cs231n.stanford.edu/
Deployment: fullstackdeeplearning.com/
FastAI: www.fast.ai/
💻 My Deep Learning Setup and Recording Setup:
www.amazon.com/shop/aladdinpe...
GitHub Repository:
github.com/aladdinpersson/Mac...
✅ One-Time Donations:
Paypal: bit.ly/3buoRYH
▶️ You Can Connect with me on:
Twitter - / aladdinpersson
LinkedIn - / aladdin-persson-a95384153
Github - github.com/aladdinpersson
Timestamps:
0:00 - Introduction
0:54 - Goal of NeRFs
2:36 - NeRF network architecture
4:35 - The key idea you need to understand
6:17 - How NeRFs learn and work
12:15 - Intuition behind volume rendering
15:15 - Loss function
15:55 - Trick #1: Positional Encoding
17:36 - Trick #2: Hierarchical sampling
19:35 - Ending