diff --git a/nerfstudio/model_components/losses.py b/nerfstudio/model_components/losses.py index 8473c46ce..e05457b0c 100644 --- a/nerfstudio/model_components/losses.py +++ b/nerfstudio/model_components/losses.py @@ -303,13 +303,12 @@ def depth_loss( raise NotImplementedError("Provided depth loss type not implemented.") -def robust_rgb_loss(rgb_outputs,rgb_gt,patch_size=16): - out_patches = rgb_outputs.view(-1,1,patch_size,patch_size) - gt_patches = rgb_gt.view(-1,1,patch_size,patch_size) +def robust_rgb_loss(rgb_gt,rgb_outputs,patch_size=16): + out_patches = rgb_outputs.view(-1,1,patch_size,patch_size,3) + gt_patches = rgb_gt.view(-1,1,patch_size,patch_size,3) device = rgb_outputs.device batch_size = out_patches.shape[0] - residuals = (out_patches - gt_patches)**2 - + residuals = torch.mean((out_patches - gt_patches)**2,dim=-1) with torch.no_grad(): med_residual = torch.median(residuals) #equation 8 @@ -317,8 +316,11 @@ def robust_rgb_loss(rgb_outputs,rgb_gt,patch_size=16): #equation 9 blurred_w = (torch.nn.functional.conv2d(weight,(1/9.)*torch.ones((1,1,3,3),device=device),padding='same')>0.5).float() expected_w = torch.mean(torch.mean(blurred_w,dim=-1),dim=-1) + #equation 10 weight_r8 = (expected_w > 0.6).float() w_8x8 = weight_r8[...,None] * torch.ones((batch_size,8,8),device=device) - final_w = torch.zeros((batch_size,16,16),device=device) - final_w[:,4:12,4:12] = w_8x8 - return torch.mean(residuals*final_w) \ No newline at end of file + final_w = torch.zeros((batch_size,patch_size,patch_size),device=device) + final_w[:, + (patch_size//2-patch_size//4):(patch_size//2+patch_size//4), + (patch_size//2-patch_size//4):(patch_size//2+patch_size//4)] = w_8x8 + return torch.mean(residuals.squeeze()*final_w) \ No newline at end of file