Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- computer-vision
|
| 5 |
+
- pytorch
|
| 6 |
+
- volumetric-video
|
| 7 |
+
- multimedia-systems
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# ReVo: Reliable Volumetric Videoconferencing via Cross-Layer Neural Loss Recovery
|
| 11 |
+
|
| 12 |
+
This repository contains the pre-trained neural loss recovery module checkpoints for the **ReVo** system. These models are designed to perform neural loss recovery for volumetric videoconferencing systems, recovering lost packets across different video codecs.
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
|
| 16 |
+
The repository includes 6 distinct models, organized by the compression codec and the spatial modality.
|
| 17 |
+
|
| 18 |
+
**Supported Codecs:**
|
| 19 |
+
* `h264` (Advanced Video Coding)
|
| 20 |
+
* `h265` (High Efficiency Video Coding / HEVC)
|
| 21 |
+
* `dcvcrt` (Deep Contextual Video Compression)
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
## Repository Structure
|
| 26 |
+
```text
|
| 27 |
+
umass-lass/ReVo
|
| 28 |
+
├── h264/
|
| 29 |
+
│ ├── h264_rgb.pth
|
| 30 |
+
│ ├── h264_depth.pth
|
| 31 |
+
├── h265/
|
| 32 |
+
│ ├── h265_rgb.pth
|
| 33 |
+
│ ├── h265_depth.pth
|
| 34 |
+
└── dcvcrt/
|
| 35 |
+
├── dcvcrt_rgb.pth
|
| 36 |
+
├── dcvcrt_depth.pth
|