camera coordinate convention

[DianChen-TRI]

Hi team, thanks for the great work! I'm wondering what camera coordinate system you're using. the look_at_matrix function in camera_utils.py looks a bit confusing to me:

def look_at_matrix(camera_pos, target, invert_pos=True):
    """Creates a 4x4 look-at matrix, keeping the camera pointing towards a target."""
    forward = (target - camera_pos).float()
    forward = forward / torch.norm(forward)

    up = torch.tensor([0.0, 1.0, 0.0], device=camera_pos.device)  # assuming Y-up coordinate system
    right = torch.cross(up, forward)
    right = right / torch.norm(right)
    up = torch.cross(forward, right)

    look_at = torch.eye(4, device=camera_pos.device)
    look_at[0, :3] = right
    look_at[1, :3] = up
    look_at[2, :3] = forward
    look_at[:3, 3] = (-camera_pos) if invert_pos else camera_pos

    return look_at

it seems to me your camera coordinate system is X-left (unlike what the name "right" suggests), Y-up, Z-forward? Then how is this used together with VIPE's convention which is X-right, Y-down, Z-forward?