Error when using RGBD mode with depth obtained by monocular depth estimate

[Blissy-32]

ORB-SLAM2 Copyright (C) 2014-2016 Raul Mur-Artal, University of Zaragoza. This program comes with ABSOLUTELY NO WARRANTY; This is free software, and you are welcome to redistribute it under certain conditions. See LICENSE.txt.

Input sensor was set to: RGB-D

Loading ORB Vocabulary. This could take a while... Vocabulary loaded in 2.61s

Camera Parameters:

• fx: 499.495
• fy: 498.644
• cx: 321.652
• cy: 177.204
• k1: 0.347873
• k2: -1.5261
• k3: 1.96932
• p1: 0.00227859
• p2: 0.00251658
• fps: 30
• color order: RGB (ignored if grayscale)

ORB Extractor Parameters:

• Number of Features: 4000
• Scale Levels: 8
• Scale Factor: 1.2
• Initial Fast Threshold: 7
• Minimum Fast Threshold: 7

Depth Threshold (Close/Far Points): 0

---

Start processing sequence ... Images in the sequence: 3172

New map created with 4008 points receive a keyframe, id = 1 receive a keyframe, id = 1 generate point cloud for kf 1, size=0 terminate called after throwing an instance of 'pcl::IOException' what(): : [pcl::PCDWriter::writeBinary] Input point cloud has no data! 已放弃 (核心已转储)
I obtained a depth map using a depth estimation model, but the resulting image looks like this. How can I modify the depth map to make it look like the depth maps in the TUM RGB-D dataset?

[withnoerr]

请问你解决了吗, 我也有相同的问题