depthcrafter/utils.py

from typing import Union, List
import tempfile
import numpy as np
import PIL.Image
import matplotlib.cm as cm
import mediapy
import torch


def save_video(
    video_frames: Union[List[np.ndarray], List[PIL.Image.Image]],
    output_video_path: str = None,
    fps: int = 10,
    crf: int = 18,
) -> str:
    if output_video_path is None:
        output_video_path = tempfile.NamedTemporaryFile(suffix=".mp4").name

    if isinstance(video_frames[0], np.ndarray):
        video_frames = [(frame * 255).astype(np.uint8) for frame in video_frames]

    elif isinstance(video_frames[0], PIL.Image.Image):
        video_frames = [np.array(frame) for frame in video_frames]
    mediapy.write_video(output_video_path, video_frames, fps=fps, crf=crf)
    return output_video_path


class ColorMapper:
    # a color mapper to map depth values to a certain colormap
    def __init__(self, colormap: str = "inferno"):
        self.colormap = torch.tensor(cm.get_cmap(colormap).colors)

    def apply(self, image: torch.Tensor, v_min=None, v_max=None):
        # assert len(image.shape) == 2
        if v_min is None:
            v_min = image.min()
        if v_max is None:
            v_max = image.max()
        image = (image - v_min) / (v_max - v_min)
        image = (image * 255).long()
        image = self.colormap[image]
        return image


def vis_sequence_depth(depths: np.ndarray, v_min=None, v_max=None):
    visualizer = ColorMapper()
    if v_min is None:
        v_min = depths.min()
    if v_max is None:
        v_max = depths.max()
    res = visualizer.apply(torch.tensor(depths), v_min=v_min, v_max=v_max).numpy()
    return res