Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,151 Bytes
5f9d349 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use
# under the terms of the LICENSE.md file.
#
# For inquiries contact [email protected]
#
import torch
from torch import nn
import numpy as np
from utils.graphics_utils import getWorld2View2, getProjectionMatrix
from utils.general_utils import PILtoTorch
import cv2
class Camera(nn.Module):
def __init__(self, resolution, colmap_id, R, T, FoVx, FoVy, depth_params, image, invdepthmap,
image_name, uid,
trans=np.array([0.0, 0.0, 0.0]), scale=1.0, data_device = "cuda",
train_test_exp = False, is_test_dataset = False, is_test_view = False
):
super(Camera, self).__init__()
self.uid = uid
self.colmap_id = colmap_id
self.R = R
self.T = T
self.FoVx = FoVx
self.FoVy = FoVy
self.image_name = image_name
try:
self.data_device = torch.device(data_device)
except Exception as e:
print(e)
print(f"[Warning] Custom device {data_device} failed, fallback to default cuda device" )
self.data_device = torch.device("cuda")
resized_image_rgb = PILtoTorch(image, resolution)
gt_image = resized_image_rgb[:3, ...]
self.alpha_mask = None
if resized_image_rgb.shape[0] == 4:
self.alpha_mask = resized_image_rgb[3:4, ...].to(self.data_device)
else:
self.alpha_mask = torch.ones_like(resized_image_rgb[0:1, ...].to(self.data_device))
if train_test_exp and is_test_view:
if is_test_dataset:
self.alpha_mask[..., :self.alpha_mask.shape[-1] // 2] = 0
else:
self.alpha_mask[..., self.alpha_mask.shape[-1] // 2:] = 0
self.original_image = gt_image.clamp(0.0, 1.0).to(self.data_device)
self.image_width = self.original_image.shape[2]
self.image_height = self.original_image.shape[1]
self.invdepthmap = None
self.depth_reliable = False
if invdepthmap is not None:
self.depth_mask = torch.ones_like(self.alpha_mask)
self.invdepthmap = cv2.resize(invdepthmap, resolution)
self.invdepthmap[self.invdepthmap < 0] = 0
self.depth_reliable = True
if depth_params is not None:
if depth_params["scale"] < 0.2 * depth_params["med_scale"] or depth_params["scale"] > 5 * depth_params["med_scale"]:
self.depth_reliable = False
self.depth_mask *= 0
if depth_params["scale"] > 0:
self.invdepthmap = self.invdepthmap * depth_params["scale"] + depth_params["offset"]
if self.invdepthmap.ndim != 2:
self.invdepthmap = self.invdepthmap[..., 0]
self.invdepthmap = torch.from_numpy(self.invdepthmap[None]).to(self.data_device)
self.zfar = 100.0
self.znear = 0.01
self.trans = trans
self.scale = scale
self.world_view_transform = torch.tensor(getWorld2View2(R, T, trans, scale)).transpose(0, 1).cuda()
self.projection_matrix = getProjectionMatrix(znear=self.znear, zfar=self.zfar, fovX=self.FoVx, fovY=self.FoVy).transpose(0,1).cuda()
self.full_proj_transform = (self.world_view_transform.unsqueeze(0).bmm(self.projection_matrix.unsqueeze(0))).squeeze(0)
self.camera_center = self.world_view_transform.inverse()[3, :3]
class MiniCam:
def __init__(self, width, height, fovy, fovx, znear, zfar, world_view_transform, full_proj_transform):
self.image_width = width
self.image_height = height
self.FoVy = fovy
self.FoVx = fovx
self.znear = znear
self.zfar = zfar
self.world_view_transform = world_view_transform
self.full_proj_transform = full_proj_transform
view_inv = torch.inverse(self.world_view_transform)
self.camera_center = view_inv[3][:3]
|