utils/point_utils.py

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import os, cv2
import matplotlib.pyplot as plt
import math
import point_cloud_utils as pcu
from pdb import set_trace as st

def depths_to_points_2(world_view_transform, tanfov, W, H, depthmap):
    c2w = (world_view_transform).inverse()
    # W, H = view.image_width, view.image_height

    # fx = W / (2 * math.tan(view.FoVx / 2.))
    # fy = H / (2 * math.tan(view.FoVy / 2.))

    fx = W / (2 * tanfov)
    fy = H / (2 * tanfov)

    intrins = torch.tensor(
        [[fx, 0., W/2.],
        [0., fy, H/2.],
        [0., 0., 1.0]]
    ).float().cuda()
    grid_x, grid_y = torch.meshgrid(torch.arange(W, device='cuda').float(), torch.arange(H, device='cuda').float(), indexing='xy')
    points = torch.stack([grid_x, grid_y, torch.ones_like(grid_x)], dim=-1).reshape(-1, 3)
    rays_d = points @ intrins.inverse().T @ c2w[:3,:3].T
    rays_o = c2w[:3,3]
    points = depthmap.reshape(-1, 1) * rays_d + rays_o
    return points



def depths_to_points(view, depthmap):
    c2w = (view.world_view_transform.T).inverse()
    W, H = view.image_width, view.image_height
    fx = W / (2 * math.tan(view.FoVx / 2.))
    fy = H / (2 * math.tan(view.FoVy / 2.))
    intrins = torch.tensor(
        [[fx, 0., W/2.],
        [0., fy, H/2.],
        [0., 0., 1.0]]
    ).float().cuda()
    grid_x, grid_y = torch.meshgrid(torch.arange(W, device='cuda').float(), torch.arange(H, device='cuda').float(), indexing='xy')
    points = torch.stack([grid_x, grid_y, torch.ones_like(grid_x)], dim=-1).reshape(-1, 3)
    rays_d = points @ intrins.inverse().T @ c2w[:3,:3].T
    rays_o = c2w[:3,3]
    points = depthmap.reshape(-1, 1) * rays_d + rays_o
    return points

def depth_to_normal(view, depth):
    """
        view: view camera
        depth: depthmap 
    """
    points = depths_to_points(view, depth).reshape(*depth.shape[1:], 3)
    output = torch.zeros_like(points)
    dx = torch.cat([points[2:, 1:-1] - points[:-2, 1:-1]], dim=0)
    dy = torch.cat([points[1:-1, 2:] - points[1:-1, :-2]], dim=1)
    normal_map = torch.nn.functional.normalize(torch.cross(dx, dy, dim=-1), dim=-1)
    output[1:-1, 1:-1, :] = normal_map
    return output

def depth_to_normal_2(world_view_transform, tanfov, W, H, depth):
    """
        view: view camera
        depth: depthmap 
    """
    points = depths_to_points_2(world_view_transform, tanfov, W, H, depth).reshape(*depth.shape[1:], 3)
    # st()
    # pcu.save_mesh_v( f'tmp/depth2pts.ply', points.detach().reshape(-1,3).cpu().numpy(),)
    output = torch.zeros_like(points)
    dx = torch.cat([points[2:, 1:-1] - points[:-2, 1:-1]], dim=0)
    dy = torch.cat([points[1:-1, 2:] - points[1:-1, :-2]], dim=1)
    normal_map = torch.nn.functional.normalize(torch.cross(dx, dy, dim=-1), dim=-1)
    output[1:-1, 1:-1, :] = normal_map
    return output