LN3Diff_I23D / utils /infer_utils.py
NIRVANALAN
init
11e6f7b
# copied from InstantMesh
import os
import imageio
import rembg
import torch
import numpy as np
import PIL.Image
from PIL import Image
from typing import Any
def resize_to_224(img):
img = transforms.functional.resize(img, 224,
interpolation=transforms.InterpolationMode.LANCZOS)
return img
def remove_background(image: PIL.Image.Image,
rembg_session: Any = None,
force: bool = False,
**rembg_kwargs,
) -> PIL.Image.Image:
do_remove = True
if image.mode == "RGBA" and image.getextrema()[3][0] < 255:
do_remove = False
do_remove = do_remove or force
if do_remove:
image = rembg.remove(image, session=rembg_session, **rembg_kwargs)
return image
def resize_foreground(
image: PIL.Image.Image,
ratio: float,
) -> PIL.Image.Image:
image = np.array(image)
assert image.shape[-1] == 4
alpha = np.where(image[..., 3] > 0)
y1, y2, x1, x2 = (
alpha[0].min(),
alpha[0].max(),
alpha[1].min(),
alpha[1].max(),
)
# crop the foreground
fg = image[y1:y2, x1:x2]
# pad to square
size = max(fg.shape[0], fg.shape[1])
ph0, pw0 = (size - fg.shape[0]) // 2, (size - fg.shape[1]) // 2
ph1, pw1 = size - fg.shape[0] - ph0, size - fg.shape[1] - pw0
new_image = np.pad(
fg,
((ph0, ph1), (pw0, pw1), (0, 0)),
mode="constant",
constant_values=((0, 0), (0, 0), (0, 0)),
)
# compute padding according to the ratio
new_size = int(new_image.shape[0] / ratio)
# pad to size, double side
ph0, pw0 = (new_size - size) // 2, (new_size - size) // 2
ph1, pw1 = new_size - size - ph0, new_size - size - pw0
new_image = np.pad(
new_image,
((ph0, ph1), (pw0, pw1), (0, 0)),
mode="constant",
constant_values=((0, 0), (0, 0), (0, 0)),
)
new_image = PIL.Image.fromarray(new_image)
return new_image