Add model card
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
pipeline_tag: image-feature-extraction
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# M3: 3D-Spatial MultiModal Memory
|
| 7 |
+
|
| 8 |
+
This repository contains the M3 model as presented in [M3: 3D-Spatial MultiModal Memory](https://huggingface.co/papers/2503.16413). M3 is a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. It integrates 3D Gaussian Splatting techniques with foundation models to build a multimodal memory capable of rendering feature representations across granularities.
|
| 9 |
+
|
| 10 |
+
Project page: https://m3-spatial-memory.github.io
|
| 11 |
+
|
| 12 |
+
Code: https://github.com/MaureenZOU/m3-spatial
|