JING Yibo

Normally camera intrinsics information is stored in sensor_msgs/CameraInfo message, see #12

> No I haven't. There are several poorly written parts in data loader that take up huge resources and one of them is https://github.com/chrischoy/FCGF/blob/master/lib/data_loaders.py#L257 which uses parallel KD trees to...

I was able to compile both glow and point_labeler on Windows10 64 bit with mingw64, with mostly cmake adaptation and compeletion, BUT with mingw64 7.3.0 and Qt5.13 the labeler is...

> I'm getting the following error > > ``` > /home/byteowl/catkin_workspace/src/stereo-dense-reconstruction/src/dense_reconstruction.cpp:13:69: fatal error: stereo_dense_reconstruction/CamToRobotCalibParamsConfig.h: No such file or directory > #include > ^ > compilation terminated. > ``` > >...

The reconstruction looks correct, it's done using `automatic reconstruction` on the demo `south building`.

+1, maybe anyone could offer some sights on how to implement autosave functionality

Upvote on the integration of 3rd party learning-based MVS methods. With the recent popularity of colmap amongst the greater CV community, and the advancements in the learning-based SfM & MVS...

look forward to any progress, would be nice to offer a python interface for the file IO like [colmap](https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py), facilitating developement of the addon

> The ray sampling and integrated position encoding in mip-nerf seems to require substantial changes to the current ray sampling implementation. Combining the mip-nerf sampling strategy should lead to major...

@sume-cn Where did you download the raw KITTI dataset with velodyne data in pcap format? How to download the raw data for a specific KITTI odometry sequence? Thanks