From deeba9833570fce09dd4da393f6318475e85a735 Mon Sep 17 00:00:00 2001
From: xxlong0 <60975977+xxlong0@users.noreply.github.com>
Date: Thu, 30 May 2024 10:46:28 +0800
Subject: [PATCH] Update README.md

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index ab77ccf..c073e68 100644
--- a/README.md
+++ b/README.md
@@ -11,6 +11,7 @@ Wonder3D reconstructs highly-detailed textured meshes from a single-view image i
 - Fixed a severe training bug. The "zero_init_camera_projection" in 'configs/train/stage1-mix-6views-lvis.yaml' should be False. Otherwise, the domain control and pose control will be invalid in the training.
 - 2024.03.19 Checkout our new model [GeoWizard](https://github.com/fuxiao0719/GeoWizard) that jointly produces depth and normal with high fidelity from single images.
 - 2024.05.24 We release a large 3D native diffusion model [CraftsMan3D](https://github.com/wyysf-98/CraftsMan) that is directly trained on 3D representation and therefore is capable of producing complex structures.
+- 2024.05.29 We release a more powerful MV cross-domain diffusion model [Era3D](https://github.com/pengHTYX/Era3D) that jointly produces 512x512 color images and normal maps, but more importantly Era3D could automatically figure out the focal length and elevation degree of the input image so that avoid geometry distortions.
 
 ## Usage
 ```bash