wbhu-tc nielsr HF Staff commited on
Commit
4150ea0
Β·
verified Β·
1 Parent(s): 50fd9b3

Correct pipeline tag and update tags (#1)

Browse files

- Correct pipeline tag and update tags (6a17d52607d0e5129072986c59bbbb3afe7e3198)


Co-authored-by: Niels Rogge <[email protected]>

Files changed (1) hide show
  1. README.md +14 -7
README.md CHANGED
@@ -1,14 +1,13 @@
1
  ---
2
- library_name: geometry-crafter
3
- license: other
4
- language:
5
- - en
6
  base_model:
7
  - tencent/DepthCrafter
8
  - stabilityai/stable-video-diffusion-img2vid-xt
9
- pipeline_tag: depth-estimation
 
 
 
 
10
  tags:
11
- - video-to-4d
12
  - point-cloud
13
  ---
14
 
@@ -43,7 +42,7 @@ If you find GeometryCrafter useful, **please help ⭐ this repo**, which is impo
43
 
44
  ## πŸ“ Introduction
45
 
46
- We present GeometryCrafter, a novel approach that estimates temporally consistent, high-quality point maps from open-world videos, facilitating downstream applications such as 3D/4D reconstruction and depth-based video editing or generation.
47
 
48
  Release Notes:
49
  - `[01/04/2025]` πŸ”₯πŸ”₯πŸ”₯**GeometryCrafter** is released now, have fun!
@@ -138,3 +137,11 @@ Please check the `evaluation` folder.
138
 
139
  - Welcome to open issues and pull requests.
140
  - Welcome to optimize the inference speed and memory usage, e.g., through model quantization, distillation, or other acceleration techniques.
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
 
2
  base_model:
3
  - tencent/DepthCrafter
4
  - stabilityai/stable-video-diffusion-img2vid-xt
5
+ language:
6
+ - en
7
+ library_name: geometry-crafter
8
+ license: other
9
+ pipeline_tag: video-to-3d
10
  tags:
 
11
  - point-cloud
12
  ---
13
 
 
42
 
43
  ## πŸ“ Introduction
44
 
45
+ We present GeometryCrafter, a novel approach that estimates temporally consistent, high-quality point maps from open-world videos, facilitating downstream applications such as 3D/4D reconstruction and depth-based video editing or generation. This model is described in detail in the paper [GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors](https://arxiv.org/abs/2504.01016).
46
 
47
  Release Notes:
48
  - `[01/04/2025]` πŸ”₯πŸ”₯πŸ”₯**GeometryCrafter** is released now, have fun!
 
137
 
138
  - Welcome to open issues and pull requests.
139
  - Welcome to optimize the inference speed and memory usage, e.g., through model quantization, distillation, or other acceleration techniques.
140
+
141
+ ## πŸ“œ Citation
142
+
143
+ If you find this work helpful, please consider citing:
144
+
145
+ ```BibTeXw
146
+ TODO
147
+ ```