-
There is now also vif (Visual Information Fidelity), and soon identity and msad (Mean Sum of Squared Differences).
They also supports slice threading and timeline (calculating quality metrics only …
-
## Feature
## Motivation
## Additional context
-
Hi,
Thanks for this tool. I use both pytorch_mssim.ssim and skimage.measure.compare_ssim to compute ssim, but the results are different. For example, ssim evaluation on an image sequence:
pytorch_ms…
-
Hello, I want to reproduce the results of your MS-SSIM experiment, but the performance is always not good. It may be because there is an error in the loss function. If it is convenient, can you releas…
-
In `p32.ssim_main`, there is`real_data = data_tmp.reshape(-1, 3, 32, 32)`. However, when computing the mssim the image size should be larger than 32. How to solve this problem?
-
Hi,
I have trained this model following the settings in your paper (batch size 32, on BSDS dataset, 500 epochs, the lr decay etc), but I found I cannot obtain the same MS-SSIM result mentioned in you…
-
python main_test_rvrt.py --task 006_RVRT_videodenoising_DAVIS_16frames --sigma 50 --folder_lq C:/RVRT/testsets/Set8/ --folder_gt C:/RVRT/testsets/Set8/ --tile 0 256 256 --tile_overlap 2 20 20
Traceba…
-
The attached guetzli encoded JPEG (_695330_a2_guetzli.jpg_) contains squared artifats where other encoded images doesn't contain such artifacts. The image was created with _--quality 90_.
The attac…
-
I use the Lightroom plugin from https://github.com/ftischhauser/JPEGOptimizer/ which uses jpeg-recompress. As part of my export process I have jpeg recompression enabled, and it is failing reliably on…
-
I wanna train/finetune over my own dataset, but I didn't find the training code:)