Spaces:
Running
on
Zero
Running
on
Zero
| # Code is copied from the gaussian-splatting/utils/loss_utils.py | |
| import torch | |
| import torch.nn.functional as F | |
| from torch.autograd import Variable | |
| from math import exp | |
| def l1_loss(network_output, gt, mean=True): | |
| return torch.abs((network_output - gt)).mean() if mean else torch.abs((network_output - gt)) | |
| def l2_loss(network_output, gt): | |
| return ((network_output - gt) ** 2).mean() | |
| def gaussian(window_size, sigma): | |
| gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)]) | |
| return gauss / gauss.sum() | |
| def create_window(window_size, channel): | |
| _1D_window = gaussian(window_size, 1.5).unsqueeze(1) | |
| _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0) | |
| window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous()) | |
| return window | |
| def ssim(img1, img2, window_size=11, size_average=True, mask = None): | |
| channel = img1.size(-3) | |
| window = create_window(window_size, channel) | |
| if img1.is_cuda: | |
| window = window.cuda(img1.get_device()) | |
| window = window.type_as(img1) | |
| return _ssim(img1, img2, window, window_size, channel, size_average, mask) | |
| def _ssim(img1, img2, window, window_size, channel, size_average=True, mask = None): | |
| mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel) | |
| mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel) | |
| mu1_sq = mu1.pow(2) | |
| mu2_sq = mu2.pow(2) | |
| mu1_mu2 = mu1 * mu2 | |
| sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq | |
| sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq | |
| sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2 | |
| C1 = 0.01 ** 2 | |
| C2 = 0.03 ** 2 | |
| ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2)) | |
| if mask is not None: | |
| ssim_map = ssim_map * mask | |
| if size_average: | |
| return ssim_map.mean() | |
| else: | |
| return ssim_map.mean(1).mean(1).mean(1) | |
| def mse(img1, img2): | |
| return (((img1 - img2)) ** 2).view(img1.shape[0], -1).mean(1, keepdim=True) | |
| def psnr(img1, img2): | |
| """ | |
| Computes the Peak Signal-to-Noise Ratio (PSNR) between two single images. NOT BATCHED! | |
| Args: | |
| img1 (torch.Tensor): The first image tensor, with pixel values scaled between 0 and 1. | |
| Shape should be (channels, height, width). | |
| img2 (torch.Tensor): The second image tensor with the same shape as img1, used for comparison. | |
| Returns: | |
| torch.Tensor: A scalar tensor containing the PSNR value in decibels (dB). | |
| """ | |
| mse = (((img1 - img2)) ** 2).view(img1.shape[0], -1).mean(1, keepdim=True) | |
| return 20 * torch.log10(1.0 / torch.sqrt(mse)) | |
| def tv_loss(image): | |
| """ | |
| Computes the total variation (TV) loss for an image of shape [3, H, W]. | |
| Args: | |
| image (torch.Tensor): Input image of shape [3, H, W] | |
| Returns: | |
| torch.Tensor: Scalar value representing the total variation loss. | |
| """ | |
| # Ensure the image has the correct dimensions | |
| assert image.ndim == 3 and image.shape[0] == 3, "Input must be of shape [3, H, W]" | |
| # Compute the difference between adjacent pixels in the x-direction (width) | |
| diff_x = torch.abs(image[:, :, 1:] - image[:, :, :-1]) | |
| # Compute the difference between adjacent pixels in the y-direction (height) | |
| diff_y = torch.abs(image[:, 1:, :] - image[:, :-1, :]) | |
| # Sum the total variation in both directions | |
| tv_loss_value = torch.mean(diff_x) + torch.mean(diff_y) | |
| return tv_loss_value |