> especially when it comes to dynamic range

You can solve this by having multiple cameras for each vantage point, with different sensors and lenses that are optimized for different light levels. Tesla isn't doing this mind you, but with the use of multiple cameras, it should be easy enough to exceed the dynamic range of the human eye so long as you are auto-selecting whichever camera is getting you the correct exposure at any given point.

Tesla claims that their cameras use "photon counting" and that this lets them see well in the dark, in fog, in heavy rain, and when facing bright lights like the sun.

Photon counting is a real thing [1] but that's not what Tesla claims to be doing.

I cannot tell if what they are doing is something actually effective that they should have called something other than "photon counting" or just the usual Musk exaggerations. Anyone here familiar with the relevant fields who can say which it is?

Here's what they claim, as summarized by whatever it is Google uses for their "AI Overview".

> Tesla photon counting is an advanced, raw-data approach to camera imaging for Autopilot and Full Self-Driving (FSD), where sensors detect and count individual light particles (photons) rather than processing aggregate image intensity. By removing traditional image processing filters and directly passing raw pixel data to neural networks, Tesla improves dynamic range, enabling better vision in low light and high-contrast scenarios.

It says these are the key aspects:

> Direct Data Processing: Instead of relying on image signal processors (ISPs) to create a human-friendly picture, Tesla feeds raw sensor data directly into the neural network, allowing the system to detect subtle light variations and near-IR (infrared) light.

> Improved Dynamic Range: This approach allows the system to see in the dark exceptionally well by not losing information to standard image compression or exposure adjustments.

> Increased Sensitivity: By operating at the single-photon level, the system achieves a higher signal-to-noise ratio, effectively "seeing in the dark".

> Elimination of Exposure Limitations: The technique helps mitigate issues like sun glare, allowing for better visibility in extreme lighting conditions.

> Neural Network Training: The raw, unfiltered data is used to train Tesla's neural networks, allowing for more robust, high-fidelity perception in complex, real-world driving environments.

[1] https://en.wikipedia.org/wiki/Photon_counting

https://www.sony-semicon.com/files/62/pdf/p-15_IMX490.pdf

The IMX490 has a dynamic range of 140dB when spitting out actual images. The neural net could easily be trained on multiexposure to account for both extremely low and extremely high light. They are not trying to create SDR images.

Please lets stop with the dynamic range bullshit. Point your phone at the sun when you're blinded in your car next time. Or use night mode. Both see better than you.

Clearly they have not reached parity, as evidenced by the crash rate of Tesla.

It's far from clear that the current HW4 + sensor suite will ever be sufficient for L4.

>reach parity at about the same time

Nah, Waymo is much safer than Tesla today, while Tesla has way-mo* data to train on and much more compute capacity in their hands. They're in a dead end.

Camera-only was a massive mistake. They'll never admit to that because there's now millions of cars out there that will be perceived as defective if they do. This is the decision that will sink Tesla to the ground, you'll see. But hail Karpathy, yeah.

* Sorry, I couldn't resist.

in contrast, a toddler equipped with an ion thruster & a modest quantity of xeon propellant could achieve enough delta-v to attain cheetah-escape velocity, provided the initial trajectory during the first 31 hours of the mission was through a low-cheetah-density environment