this post was submitted on 21 Jun 2023
72 points (100.0% liked)
World News
22057 readers
74 users here now
Breaking news from around the world.
News that is American but has an international facet may also be posted here.
Guidelines for submissions:
- Where possible, post the original source of information.
- If there is a paywall, you can use alternative sources or provide an archive.today, 12ft.io, etc. link in the body.
- Do not editorialize titles. Preserve the original title when possible; edits for clarity are fine.
- Do not post ragebait or shock stories. These will be removed.
- Do not post tabloid or blogspam stories. These will be removed.
- Social media should be a source of last resort.
These guidelines will be enforced on a know-it-when-I-see-it basis.
For US News, see the US News community.
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Don't have the paper, my info comes mainly from various interviews with people involved in the thing. Elon of course, Andrej Karpathy is the other (he was in charge of their AI program for some time).
They apparently used to use feature detection and object recognition in RGB images, then gave up on that (as generating coherent RGB images just adds latency and object recognition was too inflexible) and they're now just going by raw photon count data from the sensor fed directly into the neural nets that generate the 3d model. Once trained this apparently can do some insane stuff like pull edge data out from below the noise floor.
This may be of interest-- This is also from 2 years ago, before Tesla switched to occupancy networks everywhere. I'd say that's a pretty good equivalent of a LiDAR scan...
I Googled it to see because I thought they maybe were using event cameras then but no, they use 10bit instead of classic 8bit but they are not litterally counting photons (which would not be useful). It’s interesting that it improved the precision and recall of their « object detection model ». Guess the image is of better quality then.
The link from 2 years ago is not particularly impressive: https://arxiv.org/abs/1406.2283 this is an equal valent paper I think from 2014
Not sure the exact details- I heard they were sampling 10 bits per pixel but a bunch of their release notes talked about photon count detection back when they switched to that system.
Given that the HW3 cameras started being used to just generate RGB images, I suspect the current iteration is working by just pulling RAW format frames and interpreting them as a photon count grid, from there detecting edges and geometry with the occupancy network.
I've not seen much of anything published by Tesla on the subject. I suspect most of their research they are keeping hush hush to get a leg up on the competition. They share everything regarding EV tech because they want to push the industry in that direction, but I think they see FSD as their secret sauce that they might sell hardware kits but not let others too far under the hood.
I think you are absolutely correct for the interpretation of the photon count :)