-
I find that you use unprocessed video + PG noise model to generate enough training video pairs, then tuning with the real video dataset.
Considering the train/dev real scenes is 6, and the unpro…
-
I try to generate the synthesis dataset using the blender and SUNCG, but i have the question。you set a new camera for every scene,how do you get the room_camera.txt (which have the information about t…
-
I wanted to know if you by any chance could also upload the pretrained models for the scene synthesis example so that I don't spend time training a model and can test out the performance right away.
…
-
Hello.
After reading your paper, while using this technology, I have a question about how to assign the recommended material to the scene.
Page 4 of the paper says "Automatic Workflow - randomly a…
-
I have two drone datasets. One of the datasets, where the pose of the image was obtained by colmap, but the camera orientation was not along a specific axis, was converted to nerfstudio data format,…
-
Hello, your article is really wonderful, I am also very interested in your work, I have tried to generate a reasonable indoor 3D layout using Sun RGB-D data. But I don't know the specific implementati…
-
![image](https://user-images.githubusercontent.com/28867789/175860738-e11d8734-d93e-4d56-80d7-2286e1f5b640.png)
1. how many images are use in training? 40k or the updated full 118k?
As shown in …
-
This is what a framework that is trying to do A11y in WebGL looks like:
https://github.com/pmndrs/react-three-a11y
What can we do as an API to take the baton from where they are and allow WebXR sc…
-
Hi @chingswy, @cvxzhou, and others,
I had a query about the pre-processed [soccer data](https://chingswy.github.io/easymocap-public-doc/works/multinb.html) provided as part of the code release of t…
-
Hi, thank you for excellent work!
I noticed that the final point cloud is generated from depths of 4 target views.
My concern is that when using depth to generate point clouds, first instinct sho…