Instructions to use lucashoefs/sam-vtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use lucashoefs/sam-vtp with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("lucashoefs/sam-vtp") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained("lucashoefs/sam-vtp") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>) # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
Set citation to TBD and remove the dataset paper link
Browse files
README.md
CHANGED
|
@@ -66,14 +66,8 @@ Inputs must be metric depth and your own camera intrinsics. Wrong values produce
|
|
| 66 |
|
| 67 |
## Citation
|
| 68 |
|
| 69 |
-
|
| 70 |
-
@misc{hoefs2026samvtp,
|
| 71 |
-
title = {{SAM-VTP}: Video Memory and Measured Geometry for Continuous Traversability Segmentation},
|
| 72 |
-
author = {Hoefs, Lucas and Xie, Hui and An, Senjian and Zhang, Fangyi},
|
| 73 |
-
year = {2026}
|
| 74 |
-
}
|
| 75 |
-
```
|
| 76 |
|
| 77 |
## License
|
| 78 |
|
| 79 |
-
Apache 2.0. These weights are fine-tuned from [SAM 2.1 Hiera-T](https://huggingface.co/facebook/sam2.1-hiera-tiny), Copyright (c) Meta Platforms, Inc. and affiliates, under Apache 2.0. Training data: [TartanGround](https://huggingface.co/datasets/theairlabcmu/TartanGround) (Patel et al.,
|
|
|
|
| 66 |
|
| 67 |
## Citation
|
| 68 |
|
| 69 |
+
TBD
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
## License
|
| 72 |
|
| 73 |
+
Apache 2.0. These weights are fine-tuned from [SAM 2.1 Hiera-T](https://huggingface.co/facebook/sam2.1-hiera-tiny), Copyright (c) Meta Platforms, Inc. and affiliates, under Apache 2.0. Training data: [TartanGround](https://huggingface.co/datasets/theairlabcmu/TartanGround) (Patel et al., 2025), under CC BY 4.0.
|