This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
tamiwiki:projects:scanning-tami [2025/02/18 12:57] – wissotsky | tamiwiki:projects:scanning-tami [2025/02/24 13:24] (current) – wissotsky | ||
---|---|---|---|
Line 1: | Line 1: | ||
<WRAP center round todo 60%> | <WRAP center round todo 60%> | ||
- | Very WIP page(as of 18th February 2025), you can help by asking questions in the telegram group or in-person on Mondays | + | Very WIP page(as of 24th February 2025), you can help by asking questions in the telegram group or in-person on Mondays |
</ | </ | ||
Line 23: | Line 23: | ||
After that I switched to superpoint for the feature detection and lightglue for feature matching which seems to be a fairly popular combo currently. | After that I switched to superpoint for the feature detection and lightglue for feature matching which seems to be a fairly popular combo currently. | ||
+ | |||
+ | {{tamiwiki: | ||
First I matched every frame with its 30 nearest frames(by time). | First I matched every frame with its 30 nearest frames(by time). | ||
Line 58: | Line 60: | ||
I was able smooth the depth over by rasterizing the median depth(according to RaDe-GS) | I was able smooth the depth over by rasterizing the median depth(according to RaDe-GS) | ||
+ | |||
+ | {{tamiwiki: | ||
But I still had some outliers in the depth data. | But I still had some outliers in the depth data. | ||
Line 70: | Line 74: | ||
I was able to fit a kernel density estimate to the depth data and then I manually found cutoff value where if the density after the global peak becomes lower it means that were past the primary peak any depth beyond that is an outlier. | I was able to fit a kernel density estimate to the depth data and then I manually found cutoff value where if the density after the global peak becomes lower it means that were past the primary peak any depth beyond that is an outlier. | ||
+ | |||
+ | {{tamiwiki: | ||
After removing the depth outliers I was able to get much cleaner results | After removing the depth outliers I was able to get much cleaner results | ||
- | #TODO tsdf integration | + | To get a mesh from the depth images I used TSDF integration, I used the VoxelBlockGrid implementation from open3d. |
+ | |||
+ | But the gpu vram wasnt enough for me to extract mesh detail down to 1mm. And running the integration purely on cpu was too slow. | ||
+ | |||
+ | So I ended up computing the tsdf volume in batches on the gpu and them merging them onto a uniform voxel grid on the cpu, where there was overlap between the grids I used trilinear interpolation. | ||
- | mesh compresson | + | #TODO mesh compresson |
voxelization | voxelization |