def get_rays_np(H, W, K, c2w):
The fourth parameter is c2w matrix, which seems obviously transformation matrix of camera to world coordinates.
However, according to the code below,
rays = np.stack([get_rays_np(H, W, K, p) for p in poses[:,:3,:4]], 0)
it seems not c2w matrix, but w2c matrix is passed to the function because 'poses' variable has extrinsic parameter, which is 'world to camera' matrix.
Do I misunderstand something? Or does 'poses' variable have originally c2w matrix?
def get_rays_np(H, W, K, c2w):The fourth parameter is c2w matrix, which seems obviously transformation matrix of camera to world coordinates. However, according to the code below,rays = np.stack([get_rays_np(H, W, K, p) for p in poses[:,:3,:4]], 0)it seems not c2w matrix, but w2c matrix is passed to the function because 'poses' variable has extrinsic parameter, which is 'world to camera' matrix. Do I misunderstand something? Or does 'poses' variable have originally c2w matrix?