-
SinGAN is a very impressive work. But in the SR mode, I do not understand the reason why SinGAN is able to generate the correct SR image. I mean, not only the correct image size but the position of ob…
-
Hi, thanks for sharing your code. Have u tried to transform from low resolution to high resolution image, like super resolution? Do you have any suggestions if I apply it to SR problem. Thanks.
-
我使用RTX 3050 4GB运行模型,提示CUDA out of memory. Tried to allocate 72.00 MiB. GPU
我希望通过某种方式限制模型的显存占用应该怎么做?
代码:
pasd = pipeline(Tasks.image_super_resolution_pasd, model='damo/PASD_v2_image_super_resolution…
-
Hello. For the image super-resolution task, in your code, you just save the low-resolution image and the inversion results without using Eq.(7) for optimization. Could you please tell me how Eq.(7) is…
-
I would like to know what the minimum GPU memory is. I plan to complete a single channel image super-resolution task but don't have 8 GPUs🤣
-
Output of this image
![div2k0801](https://github.com/yangxy/PASD/assets/49861565/143bfe86-f90c-4e3d-a107-26828214b3c2)
is
![output0801](https://github.com/yangxy/PASD/assets/49861565/b0e9d3de-2cf4-…
-
I test ddnm on arbitrary imagenet image but did not get as good results as the demo.
The command I use is :
CUDA_VISIBLE_DEVICES=3 python main.py --resize_y --config confs/inet256.yml --path_y ./ILS…
-
I wonder if it would be possible to add code to do inference using an image/task pair?
E.g. super-resolution given an input image.
-
**Short Description**
Single-Image Super-Resolution describes the domain of enhancing image resolution for single images (as opposed to groups of images of a scene, for example). Solutions in this do…
-
## 一言でいうと
超解像(SR)のためのRDNを提案。RDNは階層的特徴を全て考慮できる方法。CNNベースのSRモデルが、オリジナルの低解像度(LR)画像から階層的特徴を全て使用するわけではないため、階層的特徴を考慮した。結果、最先端の方法に対して競争力のある性能を発揮した。
### 論文リンク
http://openaccess.thecvf.com/content_cvpr_2018/…
drkii updated
5 years ago