Pixie8888
Pixie8888
Hi, I have a question about image normalisation before LPIPS evaluation. It seems that image must be normalised to [-1, 1] before evaluation? I saw some paper normalise image to...
Hi, thanks for this wonderful work! I am wondering how can I compute backward optical flow using denseflow? e.g. optical flow from t+1 to t.
Hi, Thanks for the great work. I have question regarding the initializaton of memory bank. In the paper, it is said to initialize them as unit vector. However, in the...
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_msssim.ssim: [0.9655, 0.9500,...
Hi, Thanks for the code! I want to evaluate optical flow quantitatively by end-to-end point errors (AEPE) and percentage of erroneous pixels (FI). I didn't find any reference code. Could...
Hi, I am using TVL1 to capture optical flow on moving-mnist dataset (a digit moving randomly in a frame). But I found that it fail to capture optical flow. Any...
Dear author, I have a question about Audioset-instrument data. In "Co-Separating Sounds of Visual Objects", you mention there are **113,756/456 for unbalanced/balanced** instrument clips, respectively. But in "Learning to Separate...
Hi, Thanks for sharing the code. In the paper, you also conduct experiment on the scannet. Can you share how to compute superpoint on the scan net? I didn't find...
Hi, Thanks for sharing code! I have a question regarding computation. It seems that the computation of perceptual loss is much heavier than MSE loss. In my experiment, using perceptual...
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_msssim.ssim: [0.9655, 0.9500,...