Shop Hybrid cap w/ Tango + mp4->VisualSFM

sketchfab

A hybrid model. principal point cloud captures with Lenovo Phab2 Pro and the matterport tango app. These were exported and aligned in in meshlab. Originally transferred vertex colors to the reconstructed mesh, and then parameterized ‘trivial - per triangle’ (here). It looked remarkably good for not actually having texture, but had pinline shadow artifacts around most/all of the faces. As a followup, I made a 2:00 minute UHD video capture done on a vanilla samsung S6. then ran FFMPEG frame capture @ 2fps, and then fed all of the images through VisualSFM. This took about 30 minutes of compute time. I then used Cloud Compare scaling-alignment tool (4-point picking) to scale the Tango Mesh to match the scale of the VisualSFM model, in the hope that the raster registration could then be applied to (much better) mesh produced from the tango capture. I only did video on a subset of the overall tango scan, those (outer)sections are black.