LiheYoung/Depth-Anything
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
PythonApache-2.0
Issues
- 0
Onnx
#189 opened - 1
Distortion problem of point cloud map
#186 opened - 1
depth
#185 opened - 10
- 1
- 4
- 1
Inquiry about fisheye or 360 degree camera
#181 opened - 3
- 2
Question about training.
#179 opened - 1
如果只是一张单图,没有任何相机信息,如何得到更准确的点云
#177 opened - 1
- 1
- 8
- 2
Avoid Numpy for transforms
#173 opened - 4
- 2
Metric Depth Values
#171 opened - 1
Android Deployment Recommendation
#169 opened - 3
- 3
Utilization in VO and SLAM
#167 opened - 4
- 2
About evaluate of Depth anything
#165 opened - 1
- 1
- 1
use local model find error
#162 opened - 3
- 1
- 3
What is the unit of metric depth output
#159 opened - 1
- 2
- 1
train relative not converge
#156 opened - 1
- 3
- 1
RGBD Model
#153 opened - 1
project page is down
#152 opened - 0
为什么在depth_to_pointcloud.py中设置FL=715.0873
#151 opened - 3
- 6
- 0
About train the encoder
#148 opened - 2
- 3
- 7
Problem solved.
#145 opened - 1
- 2
About the Encoder feature
#143 opened - 4
Reducing the model size/making it lighter than the original vit-s and eventually reduce the flops.
#142 opened - 2
About convert depth map to normal map
#141 opened - 2
- 0
Align Point Cloud
#139 opened - 1
- 0
Quantization -- Discussion
#137 opened - 1