v-pnk / cadloc Goto Github PK

Hello dear author!
These two works are excellent, which is very novel for researchers working in fields related to visual localization!
I would like to consult two questions as follows:
Firstly, the 12 Scenes dataset is used as experimental data in MeshLoc. This dataset utilizes the RGB-D SLAM method to reconstruct a 3D model of the scene. MeshLoc makes use of the depth map obtained from the rendered model to recover the connection between the features on the query image and the 3D coordinates corresponding to the world coordinate system. So can I understood that the textures on the 3D model don't work? It is the geometric accuracy of the 3D model (e.g. point cloud depth accuracy and mesh construction method) that plays a role, as well as the method of rendering?
Secondly, in the article Visual Localization using Imperfect 3D Models from the Internet, CAD models are used, which is a very novel idea! Have the authors ever thought of using NERF as a rendering to complete the image retrieval, and using imperfect models (e.g. CAD models) to complete a rough localization result, and then later using this NERF network with fixed parameters to invert and optimize the rough localization result?
Looking forward to your reply! Thanks very much!

Hi, I've tried to check the Tref proveded in the benchmark page. It works well for Notre Dame A which is in obj file, however for other collada files (.dae), the transform matrix seems not quite correct as I apply the matrix in Meshlab. This also seems not correct when I export the model from Sketchup to obj file.
So my question is: how can I perform transformation correctly to those collada files in order to align them to the reference ply mesh?

Thanks for sharing the benchmark!
I've got a question on your MeshLoc visual localization process. In the paper you've mentioned that if we only have a 3D model of the scene and no database images, we use the rendered images as the database images. So the image retrieval stage used the rendered images rather than real images?
I wonder how this method performances since low textured CAD model may lead to bad retrieval results.