From 588a0a238db3f23f51440ade013e5a4b2c8de6be Mon Sep 17 00:00:00 2001
From: Jianyuan Wang <37647961+jytime@users.noreply.github.com>
Date: Sun, 13 Apr 2025 05:19:31 +0100
Subject: [PATCH] update the news about training code

---
 README.md | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 187741f..114f5a9 100644
--- a/README.md
+++ b/README.md
@@ -23,6 +23,10 @@
   year={2025}
 }
 ```
+
+## Updates
+- [Apr 13, 2025] Training code is being gradually cleaned and uploaded to the [training](https://github.com/facebookresearch/vggt/tree/training) branch. It will be merged into the main branch once finalized.
+
 ## Overview
 
 Visual Geometry Grounded Transformer (VGGT, CVPR 2025) is a feed-forward neural network that directly infers all key 3D attributes of a scene, including extrinsic and intrinsic camera parameters, point maps, depth maps, and 3D point tracks, **from one, a few, or hundreds of its views, within seconds**.
@@ -230,4 +234,4 @@ Thanks to these great repositories: [PoseDiffusion](https://github.com/facebookr
 
 
 ## License
-See the [LICENSE](./LICENSE.txt) file for details about the license under which this code is made available.
\ No newline at end of file
+See the [LICENSE](./LICENSE.txt) file for details about the license under which this code is made available.