-
thanks for your excellent job!
I have a question about synthetic ref images：`new_static_reference = ref_image*(~seg_ref) + static_reference_dyn*seg_ref`
However, I think this is still the original…
-
In the pouring dataset `/nerf_synthetic/test`, there's a mix of r_x.png and r_x_flow.png (where x is the index), should the r_x_flow.png be interpreted as the optical flow map? How are they generated?…
-
Hi, guys.
I am trying to use this useful tool to generate some synthetic images，but I had some troubles when I tried to get the object masks.
I downloaded the RealisticRendering pack and type in a c…
-
Having created some deepfakes, I started to wonder how you can extract the driving video from the generated video without additional information.
As rotation is possible, the first-order-model must…
-
## 注意
这里记录一些偶然间碰到的与显著性或者不好归类的数据集.
-
Hi,
Thanks for such a wonderful tool offering to the research community. I wanted to extract the joint keypoint information of the Jaco-2 robot arm (3D and projected coordinates) into the .json fil…
-
Hi folks,
I found that running tests that use `org.gradle.testfixtures.ProjectBuilder` + JDK 17 + test distribution (local or remote agents) results in the following:
```
[com.gradle.enterpris…
-
Currently, the setup is divided into 2 steps.
Step 1: Copute_dire.sh to generate an DIRE image from Input image(Real or Fake) (Distributed computing on N GPUS)
Step 2: demo.py to generate probabili…
-
Hi,
I've re-implemented HOGPicture to be much faster, using a single matrix multiplication.
I think this should be in the main branch, and I don't know what would happen if I simply fork the project …
-
- [x] #5
- use the bicycle model
- ~~or learn a model using deep learning and data from the actual car~~ **requires localization**
- [x] #6
- use a render engine/game engine. I think blender…