Update README.md
Browse files
README.md
CHANGED
|
@@ -3,8 +3,12 @@ license: apache-2.0
|
|
| 3 |
library_name: diffusers
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
| 6 |
# RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer
|
| 7 |
|
|
|
|
|
|
|
| 8 |
<div align="center" class="authors">
|
| 9 |
Liu Liu,
|
| 10 |
Xiaofeng Wang,
|
|
@@ -36,13 +40,13 @@ library_name: diffusers
|
|
| 36 |
</div>
|
| 37 |
|
| 38 |
<div align="center">
|
| 39 |
-
<img src="assets/pin.
|
| 40 |
|
| 41 |
---
|
| 42 |
|
| 43 |
## 🔍 Abstract
|
| 44 |
|
| 45 |
-
![RoboTransfer Pipeline](assets/robotransfer_pipeline.
|
| 46 |
|
| 47 |
**RoboTransfer** is a novel diffusion-based video generation framework tailored for robotic visual policy transfer. Unlike conventional approaches, RoboTransfer introduces **geometry-aware synthesis** by injecting **depth and normal priors**, ensuring multi-view consistency across dynamic robotic scenes. The method further supports **explicit control over scene components**, such as **background editing**, **object identity swapping**, and **motion specification**, offering a fine-grained video generation pipeline that benefits embodied learning.
|
| 48 |
|
|
|
|
| 3 |
library_name: diffusers
|
| 4 |
---
|
| 5 |
|
| 6 |
+
<div align="center">
|
| 7 |
+
|
| 8 |
# RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer
|
| 9 |
|
| 10 |
+
</div>
|
| 11 |
+
|
| 12 |
<div align="center" class="authors">
|
| 13 |
Liu Liu,
|
| 14 |
Xiaofeng Wang,
|
|
|
|
| 40 |
</div>
|
| 41 |
|
| 42 |
<div align="center">
|
| 43 |
+
<img src="assets/pin.jpg" width="50%" alt="RoboTransfer"/></div>
|
| 44 |
|
| 45 |
---
|
| 46 |
|
| 47 |
## 🔍 Abstract
|
| 48 |
|
| 49 |
+
|
| 50 |
|
| 51 |
**RoboTransfer** is a novel diffusion-based video generation framework tailored for robotic visual policy transfer. Unlike conventional approaches, RoboTransfer introduces **geometry-aware synthesis** by injecting **depth and normal priors**, ensuring multi-view consistency across dynamic robotic scenes. The method further supports **explicit control over scene components**, such as **background editing**, **object identity swapping**, and **motion specification**, offering a fine-grained video generation pipeline that benefits embodied learning.
|
| 52 |
|