Add teaser figures to model card
Browse files
README.md
CHANGED
|
@@ -21,6 +21,14 @@ From a single image, MYRIAD predicts distributions over sparse point trajectorie
|
|
| 21 |
- **Project Page**: https://compvis.github.io/myriad
|
| 22 |
- **GitHub Repository**: https://github.com/CompVis/flow-poke-transformer
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Usage
|
| 25 |
|
| 26 |
For programmatic use, the simplest way to use MYRIAD is via `torch.hub`:
|
|
|
|
| 21 |
- **Project Page**: https://compvis.github.io/myriad
|
| 22 |
- **GitHub Repository**: https://github.com/CompVis/flow-poke-transformer
|
| 23 |
|
| 24 |
+

|
| 25 |
+
*From a single image, our model envisions diverse, physically consistent futures by predicting sparse point trajectories step by step.*
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+

|
| 29 |
+
*Its efficiency enables exploring thousands of counterfactual rollouts directly in motion space - here illustrated for billiards planning, where candidate shots are evaluated by simulating many possible outcomes.*
|
| 30 |
+
|
| 31 |
+
|
| 32 |
## Usage
|
| 33 |
|
| 34 |
For programmatic use, the simplest way to use MYRIAD is via `torch.hub`:
|