-
Hi, I'm trying to run the training code on `ZJU-mocap` dataset. The code works fine with `batch_size=1` (as in `eval` scripts), but got error when `batch_size=4` (as in `train` scripts).
In [this l…
-
## Outline
Use neural net during ray tracing as an acceleration method.
## Details
Ray tracing involves computationally expensive calculations and geometry with varying degrees of complexity. …
-
Hi Sizhe,
Thanks for this fabulous work. I noticed your default checkpoint G.neural_rendering_resolution is 64 rather than 128, I wonder whether you have fine-tuned a 128 version?
Thanks and lo…
-
Thanks for the excellent work! Here I have a question regarding the neural rendering network.
As suggested in the paper, the RGB render loss of reference image boosts the depth prediction performa…
-
Hi, I've tried mcmc strategy on smaller subset (about 542 images, 150, 000 initial point cloud), which works quite good. But when I'm using the whole dataset (about 973 images, 360, 000 initial point …
-
Has anyone had this problem?
Traceback (most recent call last):
File "main.py", line 96, in
main()
File "/home/robot/miniconda3/envs/trimrf/lib/python3.8/site-packages/gin/config.py", l…
-
Hey, such an excellent work! I have a small doubt about psnr, that is, after the training phase, psnr is calculated in both the render phase and the evaluate phase, theoretically both the values sho…
-
http://science.sciencemag.org/content/360/6394/1204.full
- Deepmind
DL輪読会
- https://www.slideshare.net/DeepLearningJP2016/dlgqn-111725780
TMats updated
6 years ago
-
## 一言でいうと
シーンを認識で、A地点/B地点からの画像から、C地点からの画像を推定するというタスクを解かせた研究。各地点からの画像をネットワークで潜在表現に圧縮し、クエリ(C地点)と潜在表現から画像を生成する。これにより2Dから3Dへのレンダリングや、強化学習での学習効率の向上が行えたとのこと。
### 論文リンク
https://deepmind.com/blog/neu…
-
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is.
Yes, Image Style Transfer addresses a specific type of problem in the fiel…