I am a newbie to pytorch3d exploring supercool notebooks!
I have the following questions on pytorch3d/render_textured_meshes.ipynb at main · facebookresearch/pytorch3d · GitHub
image_grid(images.cpu().numpy(), rows=4, cols=5, rgb=True)previews the 3D object projection on to 2D view. Is there a generalizable way to extract accurate 2D object boundary mask?
img1 = images.cpu().numpy(); plt.imshow(img1) yields image of different visual quality(slightly faded and grainy) compared to the plot from #1 . why is there a difference?