[Dead_Lemon]

What is the actual objective of this, is it solving an issue or creating a solution to a problem, that is still to be determined? It seems like a lot of energy to replicate a lidar mapping system. It's not like you can expect accurate dimensions from this approximate guess work, excluding the expected hallucinations adding to inaccuracy.

[alpine01]

3D reconstruction of old spaces which no longer exist seems like a clear use case to me. There's loads of old videos of driving down a street in the 80s, or neighborhoods in cities which got replaced.

I can imagine future iterations of this which bring together other stills of the same space at that time to augment the dataset. Then perhaps another pass to fill in gaps with likely missing content based on probability or data from say the same street 10 years later.

It won't be 100% real, but I think it'd be very cool to be able to have a google-street view style experience of areas before google street view existed.

[phrotoma]

> it'd be very cool to be able to have a google-street view style experience of areas before google street view existed.

Now do Kowloon Walled City.

[voidUpdate]

Video cameras are much cheaper and easier to use than LIDAR, like anyone can just pull out their phone, take a video and send it to this algorithm to get a reasonable point cloud of the environment. Sure, if you want an exact model of an environment and you have the time and money, LIDAR would give better results, but this is about doing more with less

[washadjeffmad]

We use drones with RGB cameras for photogrammetry to reconstruct 3D environments with gaussian splatting, which is a manual process and often requires making multiple trips for additional capture to fill in gaps. Because it's for perceptual use and doesn't require high accuracy, automating with a single-take video would be useful.

[KaiserPro]

One of the key issues of "machine perception" is the inability of machines using standard image sensors to re-create the world accurately.

Lidars are great, and getting smaller, but they still eat a lot of power. (The quest 3 had a lidar on the front[well structured light] and it was mostly not used)

For machines to understand the 3d world, first they need to extract geometry, then isolate those geometries into objects. This method is _a_ way to do that, the first step, extracting 3d points.

The problem with this model is that the points are not actually that well aligned frame to frame. This is why it looks a bit blurry. I assume this is to avoid running out of memory, as you're not quite sure about which points are relevant and need to be kept in memory.

Once you have those points, you need to replace them with simplfied geometry, so that you can workout intersections and junk.

[flipbrad]

N00b question from me, perhaps, but how easy is it to mount and run Lidar on aerial drones?

[petargyurov]

It's easy but it's not cheap. Well, price is relative but capturing video is certainly cheaper.

Also, I am not sure how heavy LIDAR units are, but remember that the heavier the payload the more the flight time is reduced. Some drones can only have a single payload, so if you also want to capture (high-res) video/imgs you need to fly again.

It all depends on the use-case.

[Daub]

The most available lidar is found on your iPhone, but the results are orders of magnitude less detailed than that derived from photogrammetry. How ever an advantage is that lidar is not confused by reflections.

[taneq]

Huh? LIDAR absolutely is confused by reflections. Not always the reflections you can see (because often it’s using IR wavelengths) but nonetheless, reflections.

[ekjhgkejhgk]

The actual objective is learning about these systems. It's called research.

[_diyar]

You can reconstruct accurate dimensions if you have IMU data.