Hello. The figure left shows the 4-th channel (mesh silhouette) of the rasterized mesh. These different light/dark (marked with red) affect the loss constrain at the pixel-level, when I use a white mask as the ground truth or target image (Figure right).
I have read your paper and there are no such light and dark areas (Figure 11). Could you please tell me how to avoid the different light/dark areas in the rasterized mesh image？That is, how to display all pixels in silhouette in white (like the white mask).
Hello. The figure left shows the 4-th channel (mesh silhouette) of the rasterized mesh. These different light/dark (marked with red) affect the loss constrain at the pixel-level, when I use a white mask as the ground truth or target image (Figure right).
I have read your paper and there are no such light and dark areas (Figure 11). Could you please tell me how to avoid the different light/dark areas in the rasterized mesh image？That is, how to display all pixels in silhouette in white (like the white mask).