Spaces:
Sleeping
Sleeping
File size: 4,284 Bytes
56cd6b7 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
# Copyright (C) 2024-present Naver Corporation. All rights reserved.
# Licensed under CC BY-NC-SA 4.0 (non-commercial use only).
#
# --------------------------------------------------------
# croppping utilities
# --------------------------------------------------------
import PIL.Image
import os
os.environ["OPENCV_IO_ENABLE_OPENEXR"] = "1"
import cv2 # noqa
import numpy as np # noqa
from dust3r.utils.geometry import colmap_to_opencv_intrinsics, opencv_to_colmap_intrinsics # noqa
try:
lanczos = PIL.Image.Resampling.LANCZOS
except AttributeError:
lanczos = PIL.Image.LANCZOS
class ImageList:
""" Convenience class to aply the same operation to a whole set of images.
"""
def __init__(self, images):
if not isinstance(images, (tuple, list, set)):
images = [images]
self.images = []
for image in images:
if not isinstance(image, PIL.Image.Image):
image = PIL.Image.fromarray(image)
self.images.append(image)
def __len__(self):
return len(self.images)
def to_pil(self):
return tuple(self.images) if len(self.images) > 1 else self.images[0]
@property
def size(self):
sizes = [im.size for im in self.images]
assert all(sizes[0] == s for s in sizes)
return sizes[0]
def resize(self, *args, **kwargs):
return ImageList(self._dispatch('resize', *args, **kwargs))
def crop(self, *args, **kwargs):
return ImageList(self._dispatch('crop', *args, **kwargs))
def _dispatch(self, func, *args, **kwargs):
return [getattr(im, func)(*args, **kwargs) for im in self.images]
def rescale_image_depthmap(image, depthmap, camera_intrinsics, output_resolution):
""" Jointly rescale a (image, depthmap)
so that (out_width, out_height) >= output_res
"""
image = ImageList(image)
input_resolution = np.array(image.size) # (W,H)
output_resolution = np.array(output_resolution)
if depthmap is not None:
# can also use this with masks instead of depthmaps
assert tuple(depthmap.shape[:2]) == image.size[::-1]
assert output_resolution.shape == (2,)
# define output resolution
scale_final = max(output_resolution / image.size) + 1e-8
output_resolution = np.floor(input_resolution * scale_final).astype(int)
# first rescale the image so that it contains the crop
image = image.resize(output_resolution, resample=lanczos)
if depthmap is not None:
depthmap = cv2.resize(depthmap, output_resolution, fx=scale_final,
fy=scale_final, interpolation=cv2.INTER_NEAREST)
# no offset here; simple rescaling
camera_intrinsics = camera_matrix_of_crop(
camera_intrinsics, input_resolution, output_resolution, scaling=scale_final)
return image.to_pil(), depthmap, camera_intrinsics
def camera_matrix_of_crop(input_camera_matrix, input_resolution, output_resolution, scaling=1, offset_factor=0.5, offset=None):
# Margins to offset the origin
margins = np.asarray(input_resolution) * scaling - output_resolution
assert np.all(margins >= 0.0)
if offset is None:
offset = offset_factor * margins
# Generate new camera parameters
output_camera_matrix_colmap = opencv_to_colmap_intrinsics(input_camera_matrix)
output_camera_matrix_colmap[:2, :] *= scaling
output_camera_matrix_colmap[:2, 2] -= offset
output_camera_matrix = colmap_to_opencv_intrinsics(output_camera_matrix_colmap)
return output_camera_matrix
def crop_image_depthmap(image, depthmap, camera_intrinsics, crop_bbox):
"""
Return a crop of the input view.
"""
image = ImageList(image)
l, t, r, b = crop_bbox
image = image.crop((l, t, r, b))
depthmap = depthmap[t:b, l:r]
camera_intrinsics = camera_intrinsics.copy()
camera_intrinsics[0, 2] -= l
camera_intrinsics[1, 2] -= t
return image.to_pil(), depthmap, camera_intrinsics
def bbox_from_intrinsics_in_out(input_camera_matrix, output_camera_matrix, output_resolution):
out_width, out_height = output_resolution
l, t = np.int32(np.round(input_camera_matrix[:2, 2] - output_camera_matrix[:2, 2]))
crop_bbox = (l, t, l+out_width, t+out_height)
return crop_bbox
|