|
import os |
|
import imageio |
|
import rembg |
|
import torch |
|
import numpy as np |
|
import PIL.Image |
|
from PIL import Image |
|
from typing import Any |
|
|
|
|
|
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(), |
|
) |
|
|
|
fg = image[y1:y2, x1:x2] |
|
|
|
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)), |
|
) |
|
|
|
|
|
new_size = int(new_image.shape[0] / ratio) |
|
|
|
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 |
|
|
|
|
|
def images_to_video( |
|
images: torch.Tensor, |
|
output_path: str, |
|
fps: int = 30, |
|
) -> None: |
|
|
|
video_dir = os.path.dirname(output_path) |
|
video_name = os.path.basename(output_path) |
|
os.makedirs(video_dir, exist_ok=True) |
|
|
|
frames = [] |
|
for i in range(len(images)): |
|
frame = (images[i].permute(1, 2, 0).cpu().numpy() * 255).astype(np.uint8) |
|
assert frame.shape[0] == images.shape[2] and frame.shape[1] == images.shape[3], \ |
|
f"Frame shape mismatch: {frame.shape} vs {images.shape}" |
|
assert frame.min() >= 0 and frame.max() <= 255, \ |
|
f"Frame value out of range: {frame.min()} ~ {frame.max()}" |
|
frames.append(frame) |
|
imageio.mimwrite(output_path, np.stack(frames), fps=fps, quality=10) |
