CImg VS OpenMVG (open Multiple View Geometry)

It looks promising.

I like the way each algorithm is explained with minimal example and demo images.

I'm looking for such a lightweight vision lib to embed simple image manipulation programs on tiny ESP32-CAM boards.

OpenCV seems too heavy to integrate on such small devices.

So far, I've been able to develop simple image processing programs with CImg[1] (simple filtering, image cropping, adding text).

I'll try to spend some time exploring this SOD lib, thank you for sharing.

[1] https://cimg.eu/

CImg : http://cimg.eu/ (C++)

Try to find a community that will know more about openMVG, like the discussion tab on their github.

OpenMVG (JSON, NVM, PLY)

I find openMVG very decent, FTXUI might be a good one and nlohmann's json library is also pretty nice. I don't really know of any project that strictly adheres to the core guidelines, except maybe for some of Jason Turner's (sample) projects.

I am looking for some pointers to papers/open-source software that can do fast and accurate depth estimation from multi-view videos. I am aware of colmap and OpenMVG software but was curious to know if there are others out there that outperform these. I am also interested in any state-of-the-art for depth estimation using unsupervised or self-supervised neural networks.

OpenMVG is super cool, and the project lead Pierre is very generous with his time.

Meshroom is just a Python wrapper for VSfM. OpenMVS seems like the package most customizers are starting to use. https://github.com/openMVG/openMVG