Главная
Study mode:
on
1
Intro
2
Neural Implicit Shapes
3
NASA
4
Backward lbs
5
Training
6
Results
7
Summary
8
Examples
9
HighLevel Approach
10
MetaLearning
11
MetaLearning Example
12
MetaLearning Approach
13
MetaLearning Results
14
Fine Tuning
15
Comparison
16
Conclusion
Description:
Explore cutting-edge research on animatable human avatars in this conference talk. Delve into two groundbreaking papers: SNARF, which introduces differentiable forward skinning for animating non-rigid neural implicit shapes, and MetaAvatar, which focuses on learning animatable clothed human models from limited depth images. Gain insights into neural implicit shapes, backward LBS, meta-learning approaches, and fine-tuning techniques. Examine high-level methodologies, training processes, and comparative results. Witness examples and demonstrations that showcase the potential of these innovative techniques in creating more realistic and adaptable human avatars for various applications.

Towards Animatable Human Avatars

Andreas Geiger
Add to list
0:00 / 0:00