rays.py

import torch
from kornia import create_meshgrid


def get_ray_directions(H, W, focal):
    """
    Get ray directions for all pixels in camera coordinate.
    Reference: https://www.scratchapixel.com/lessons/3d-basic-rendering/
               ray-tracing-generating-camera-rays/standard-coordinate-systems

    Inputs:
        H, W, focal: image height, width and focal length

    Outputs:
        directions: (H, W, 3), the direction of the rays in camera coordinate
    """
    grid = create_meshgrid(H, W, normalized_coordinates=False)[0] # [H,W,2]
    i, j = grid.unbind(-1) # untangles grid
    # the direction here is without +0.5 pixel centering as calibration is not so accurate
    # see https://github.com/bmild/nerf/issues/24
    directions = \
        torch.stack([(i-W/2)/focal, -(j-H/2)/focal, -torch.ones_like(i)], -1) # (H, W, 3)

    return directions

def get_rays(directions, c2w):
    """
    Get ray origin and normalized directions in world coordinate for all pixels in one image.
    Reference: https://www.scratchapixel.com/lessons/3d-basic-rendering/
               ray-tracing-generating-camera-rays/standard-coordinate-systems

    Inputs:
        directions: (H, W, 3) precomputed ray directions in camera coordinate
        c2w: (3, 4) transformation matrix from camera coordinate to world coordinate
        c2w : [3x4] matrix defining how to go from camera coordinate to world coordinate
		R|t is w2c and Rc|C is c2w. R = Rc.T and C is camera coords
		So here we rotate rays_d w.r.t world thus multiply with Rc.T
		and rays_o is simply the last column.
		https://ksimek.github.io/2012/08/22/extrinsic/


    Outputs:
        rays_o: (H*W, 3), the origin of the rays in world coordinate
        rays_d: (H*W, 3), the normalized direction of the rays in world coordinate
    """
    # Rotate ray directions from camera coordinate to the world coordinate
    rays_d = directions @ c2w[:, :3].T # (H, W, 3)
    rays_d = rays_d / torch.norm(rays_d, dim=-1, keepdim=True)
    # The origin of all rays is the camera origin in world coordinate
    rays_o = c2w[:, 3].expand(rays_d.shape) # (H, W, 3)

    rays_d = rays_d.view(-1, 3)
    rays_o = rays_o.view(-1, 3)

    return rays_o, rays_d