Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the groundbreaking Neural Radiance Fields (NeRF) technique for view synthesis in this comprehensive video explanation. Dive into the core concepts of NeRF, including its ability to embed entire scenes into neural network weights and achieve state-of-the-art results using sparse input views. Learn about the differential volume rendering procedure, directional dependence, and how NeRF captures fine structural details, reflections, and transparency. Follow along as the video breaks down the training process, radiance field volume rendering, positional encoding, and hierarchical volume sampling. Gain insights into the experimental results and understand how NeRF outperforms prior work in neural rendering and view synthesis.
Syllabus
- Intro & Overview
- View Synthesis Task Description
- The fundamental difference to classic Deep Learning
- NeRF Core Concept
- Training the NeRF from sparse views
- Radiance Field Volume Rendering
- Resulting View Dependence
- Positional Encoding
- Hierarchical Volume Sampling
- Experimental Results
- Comments & Conclusion
Taught by
Yannic Kilcher