Image-to-3D
English
wala
depth-map-to-3d
Hooman commited on
Commit
e45e9ad
1 Parent(s): 447b002

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - depth-map-to-3d
9
  ---
10
 
11
- # Model Card for WaLa-DM4-1B
12
 
13
  This model is part of the Wavelet Latent Diffusion (WaLa) paper, capable of generating high-quality 3D shapes from single-view depth map input with detailed geometry and complex structures.
14
 
@@ -16,7 +16,7 @@ This model is part of the Wavelet Latent Diffusion (WaLa) paper, capable of gene
16
 
17
  ### Model Description
18
 
19
- WaLa-DM4-1B is a large-scale 3D generative model trained on a massive dataset of over 10 million publicly-available 3D shapes. It can efficiently generate a wide range of high-quality 3D shapes from single-view depth map input in just 4 seconds. The model uses a wavelet-based compact latent encoding and a billion-parameter architecture to achieve superior performance in terms of geometric detail and structural plausibility.
20
 
21
  - **Developed by:** Aditya Sanghi, Aliasghar Khani, Chinthala Pradyumna Reddy, Arianna Rampini, Derek Cheung, Kamal Rahimi Malekshan, Kanika Madan, Hooman Shayani
22
  - **Model type:** 3D Generative Model
@@ -45,7 +45,7 @@ The model should not be used for:
45
 
46
  - Creation of load-bearing physical objects the failure of which could cause property damage or personal injury
47
 
48
- - Any usage not in compliance with the [license](https://huggingface.co/ADSKAILab/WaLa-DM4-1B/blob/main/LICENSE.md), in particular, the "Acceptable Use" section.
49
 
50
  ## Bias, Risks, and Limitations
51
 
 
8
  - depth-map-to-3d
9
  ---
10
 
11
+ # Model Card for WaLa-DM1-1B
12
 
13
  This model is part of the Wavelet Latent Diffusion (WaLa) paper, capable of generating high-quality 3D shapes from single-view depth map input with detailed geometry and complex structures.
14
 
 
16
 
17
  ### Model Description
18
 
19
+ WaLa-DM1-1B is a large-scale 3D generative model trained on a massive dataset of over 10 million publicly-available 3D shapes. It can efficiently generate a wide range of high-quality 3D shapes from single-view depth map input in just 4 seconds. The model uses a wavelet-based compact latent encoding and a billion-parameter architecture to achieve superior performance in terms of geometric detail and structural plausibility.
20
 
21
  - **Developed by:** Aditya Sanghi, Aliasghar Khani, Chinthala Pradyumna Reddy, Arianna Rampini, Derek Cheung, Kamal Rahimi Malekshan, Kanika Madan, Hooman Shayani
22
  - **Model type:** 3D Generative Model
 
45
 
46
  - Creation of load-bearing physical objects the failure of which could cause property damage or personal injury
47
 
48
+ - Any usage not in compliance with the [license](https://huggingface.co/ADSKAILab/WaLa-DM1-1B/blob/main/LICENSE.md), in particular, the "Acceptable Use" section.
49
 
50
  ## Bias, Risks, and Limitations
51