Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
extra_gated_fields:
|
| 4 |
+
First Name: text
|
| 5 |
+
Last Name: text
|
| 6 |
+
Date of birth: date_picker
|
| 7 |
+
Country: country
|
| 8 |
+
Affiliation: text
|
| 9 |
+
Job title:
|
| 10 |
+
type: select
|
| 11 |
+
options:
|
| 12 |
+
- Student
|
| 13 |
+
- Research Graduate
|
| 14 |
+
- AI researcher
|
| 15 |
+
- AI developer/engineer
|
| 16 |
+
- Reporter
|
| 17 |
+
- Other
|
| 18 |
+
geo: ip_location
|
| 19 |
+
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
|
| 20 |
+
extra_gated_description: >-
|
| 21 |
+
The information you provide will be collected, stored, processed and shared in
|
| 22 |
+
accordance with the [Meta Privacy
|
| 23 |
+
Policy](https://www.facebook.com/privacy/policy/).
|
| 24 |
+
extra_gated_button_content: Submit
|
| 25 |
+
language:
|
| 26 |
+
- en
|
| 27 |
+
pipeline_tag: mask-generation
|
| 28 |
+
library_name: checkpoint
|
| 29 |
+
tags:
|
| 30 |
+
- sam3.1
|
| 31 |
+
---
|
| 32 |
+
# SAM 3.1
|
| 33 |
+
[SAM 3](https://github.com/facebookresearch/sam3) (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points, boxes, and masks. SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase, handling over 50x more unique concepts than existing benchmarks. SAM 3.1 builds on this with **Object Multiplex**, a shared-memory approach for joint multi-object tracking that delivers ~7x faster inference at 128 objects on a single H100 GPU without sacrificing accuracy, along with improved VOS performance on 6 out of 7 benchmarks.
|
| 34 |
+
|
| 35 |
+
<p align="center">
|
| 36 |
+
<img src="https://github.com/facebookresearch/sam3/blob/main/assets/sam3.1_diagram.png?raw=true" width="720" />
|
| 37 |
+
</p>
|
| 38 |
+
|
| 39 |
+
This repository hosts only the SAM 3.1 model checkpoints — there is no Hugging Face Transformers integration. For installation, code, usage examples, and full documentation, please visit the [SAM 3 GitHub repository](https://github.com/facebookresearch/sam3).
|