Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: pytorch
|
| 4 |
+
tags:
|
| 5 |
+
- 3d
|
| 6 |
+
- visual-question-answering
|
| 7 |
+
- spatial-reasoning
|
| 8 |
+
- ground3d-lmm
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Ground3D-LMM — CA-VQA (3D+2D)
|
| 12 |
+
|
| 13 |
+
Fine-tuned **Ground3D-LMM** checkpoint for **CA-VQA** (paper **Table 9** — generality beyond ScanNet),
|
| 14 |
+
**3D+2D (point cloud + RGB views)** setting. Reproduces the paper's Table-9 average (~48).
|
| 15 |
+
|
| 16 |
+
- **Checkpoint file:** `pytorch_model.pth`
|
| 17 |
+
- **Code:** https://github.com/AmolHarsh/ground3d-lmm
|
| 18 |
+
|
| 19 |
+
## Usage
|
| 20 |
+
```bash
|
| 21 |
+
CKPT=$(huggingface-cli download amolharsh/Ground3D-LMM-CAVQA-4B-Joint pytorch_model.pth)
|
| 22 |
+
# evaluate with the CA-VQA harness: infer_cavqa.py -> merge_preds.py -> evaluate_cavqa.py
|
| 23 |
+
```
|