模型介绍

该模型输入要求一张RGB图像，输出结果为稠密深度图。

网络结构

模型描述

该模型基于 AdaBins: Depth Estimation using Adaptive Bins；（Reference: https://arxiv.org/abs/2011.14141）

代码示例

import cv2
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.cv.image_utils import depth_to_color

task = 'image-depth-prediction'
model_id = 'Damo_XR_Lab/cv_adabins_image-depth-prediction_indoor'

estimator = pipeline(Tasks.image_depth_prediction, model=model_id)

image = '/data/test_imgs/test_rgb.jpg'
results = estimator(input=image)
depth_vis = result[OutputKeys.DEPTHS_COLOR]
cv2.imwrite('result.jpg', depth_vis)

Demo