Shing-Yan Loo

Hi again, After looking into the shape from shading example, I think I have completed the re-projection part. The only problem I have is the sampling of the image pixels...

Update: The code works without a problem. The warping should work because I tested using with its equivalent Python code. However, the energy won't go down. It says "Function tolerance...

Been stuck in this problem for two days. Using the following command works for me. Then follow the rest of the instructions as per stated. `bazel build --config=opt --config=cuda --config=monolithic...

Photometric error is being used in [stereo matching](https://github.com/tum-vision/lsd_slam/blob/d1e6f0e1a027889985d2e6b4c0fe7a90b0c75067/lsd_slam_core/src/DepthEstimation/DepthMap.cpp#L1442). In order to compute/update the depth of a pixel, they first compute the 5-equidistant points (think of it as a 'descriptor') in...

Hey, The executable is named _dataset_ in the catkinized LSD-SLAM, so you need to replace _dataset_slam_ with _dataset_: `$ rosrun lsd_slam_core dataset _files:=/home/roshnee/catkin_ws/src/T1_rectified/images _hz:=0 _calib:=/home/roshnee/catkin_ws/src/T1_rectified/calibration.yaml`

@hengshanji @Zy27 @xiupingmath I found the solution to the problem. My system was using Eigen 3.3.0, which was the exact cause to the problem. > tensorflow/core/framework/numeric_types.h:60:34: error: ‘log’/'exp'/'abs' is not...

You are right. To use MiDaS 3.0, you just have to go to `python/export_model.py` and import the `DPTDepthModel` class to convert the pre-trained model to a torchscript model.

I encountered this issue before, but I couldn't remember how I solved it. I would suggest you to run the launch file with valgrind memcheck, i.e., `` However, it can...

Do you have any hints as to which library is complaining about the error? I can only vaguely remember that previously I was having issues with OpenCV library and Nvidia...

I ran `catkin_make` to build the project. Try to remove 'devel' and 'build' folders and do `catkin_make `again.