Jiatao Gu
commited on
Commit
•
7dc8cc0
1
Parent(s):
11e651b
add models
Browse files- .gitattributes +4 -0
- README.md +8 -0
- ffhq_1024.pkl +3 -0
- ffhq_256.pkl +3 -0
- ffhq_512.pkl +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
29 |
+
ffhq_512.pkl filter=lfs diff=lfs merge=lfs -text
|
30 |
+
ffhq_256.pkl filter=lfs diff=lfs merge=lfs -text
|
31 |
+
ffhq_1024.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,11 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
---
|
4 |
+
## StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
|
5 |
+
**Abstract:** *We propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D images. Existing approaches either cannot synthesize high-resolution images with fine details or yield noticeable 3D-inconsistent artifacts. In addition, many of them lack control over style attributes and explicit 3D camera poses. StyleNeRF integrates the neural radiance field (NeRF) into a style-based generator to tackle the aforementioned challenges, i.e., improving rendering efficiency and 3D consistency for high-resolution image generation. We perform volume rendering only to produce a low-resolution feature map and progressively apply upsampling in 2D to address the first issue. To mitigate the inconsistencies caused by 2D upsampling, we propose multiple designs, including a better upsampler and a new regularization loss. With these designs, StyleNeRF can synthesize high-resolution images at interactive rates while preserving 3D consistency at high quality. StyleNeRF also enables control of camera poses and different levels of styles, which can generalize to unseen views. It also supports challenging tasks, including zoom-in and-out, style mixing, inversion, and semantic editing.*
|
6 |
+
|
7 |
+
## Model description
|
8 |
+
This is a pre-trained StyleNeRF checkpoint at a resolution of 512^2 based on the basic configuration used in the original paper.
|
9 |
+
|
10 |
+
## How to use
|
11 |
+
Please check the official opensource code at [here](https://github.com/facebookresearch/StyleNeRF).
|
ffhq_1024.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0680f819a6f1e7e9a8a24788f4517cd5e7bebda240e3042249dc8ed5c32ca9a6
|
3 |
+
size 193231581
|
ffhq_256.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d432e560821b84e9137e4425737d51333e67eb3f2171eee3d0324a2afa6ba7f
|
3 |
+
size 134274390
|
ffhq_512.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:269df002406ca93cd14a9afd27bfc796604682166588af893f78f85459617bf0
|
3 |
+
size 154818723
|