Image-to-3D
3d
dmitriitochilkin commited on
Commit
ff81a2e
1 Parent(s): c0b4494

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -11
README.md CHANGED
@@ -13,18 +13,8 @@ license: mit
13
  pipeline_tag: image-to-3d
14
  ---
15
  # TripoSR
16
-
17
- ## Model Description
18
-
19
- TripoSR is a fast and feed-forward 3D generative model developed in partnership with Tripo AI inspired by the recent work of [LRM: Large Reconstruction Model For Single Image to 3D](https://arxiv.org/abs/2311.04400).
20
-
21
  ![](figures/input800.mp4)
22
-
23
- This new image-to-3D model leverages cutting-edge AI advancements to set new standards in 3D model generation. Designed to cater to the growing demands of entertaining, gaming, industrial design, and architecture professionals, TripoSR enriches the conversion process with detail and precision while providing efficient and responsive outputs for visualizing 3D objects.
24
-
25
- ## Usage
26
-
27
- For usage instructions, please refer to our [TripoSR GitHub repository](https://github.com/VAST-AI-Research/TripoSR).
28
 
29
  ## Model Details
30
 
@@ -47,6 +37,11 @@ We closely follow [LRM](https://arxiv.org/abs/2311.04400) network architecture f
47
  We use renders from the [Objaverse](https://objaverse.allenai.org/objaverse-1.0) dataset, utilizing our enhanced rendering method that more closely replicate the distribution of images found in the real world, significantly improving our model’s ability to generalize. We selected a carefully curated subset of the Objaverse dataset for the training data, which is available under the CC-BY license.
48
 
49
 
 
 
 
 
 
50
  ### Misuse, Malicious Use, and Out-of-Scope Use
51
 
52
  The model should not be used to intentionally create or disseminate 3D models that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
 
13
  pipeline_tag: image-to-3d
14
  ---
15
  # TripoSR
 
 
 
 
 
16
  ![](figures/input800.mp4)
17
+ TripoSR is a fast and feed-forward 3D generative model developed in partnership with Tripo AI inspired by the recent work of [LRM: Large Reconstruction Model For Single Image to 3D](https://arxiv.org/abs/2311.04400).
 
 
 
 
 
18
 
19
  ## Model Details
20
 
 
37
  We use renders from the [Objaverse](https://objaverse.allenai.org/objaverse-1.0) dataset, utilizing our enhanced rendering method that more closely replicate the distribution of images found in the real world, significantly improving our model’s ability to generalize. We selected a carefully curated subset of the Objaverse dataset for the training data, which is available under the CC-BY license.
38
 
39
 
40
+ ## Usage
41
+
42
+ For usage instructions, please refer to our [TripoSR GitHub repository](https://github.com/VAST-AI-Research/TripoSR).
43
+
44
+
45
  ### Misuse, Malicious Use, and Out-of-Scope Use
46
 
47
  The model should not be used to intentionally create or disseminate 3D models that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.