Tim Field

Building the deployment stack for humanoid robots

Prev: Willow Garage, hedge fund quant
NZ → London → NYC → SF → Tahoe

[Tim Field @nobbis]

Building a software stack for humanoid robots.

Realtime 3D mapping working.

Next: navigation.

[Tim Field @nobbis]

@JacobZietek @chris_j_paxton https://t.co/cmq38NliFH

[Tim Field @nobbis]

@jon_barron Sure (see video) but this isn't their fine-tuned metric depth model – output's unitless with range close to [0, 1] every frame.

IMO fitting the depth image to VIO feature points would be more fruitful than asking a monocular system to recover accurate metric depth.

[Tim Field @nobbis]

Trying out realtime video-to-depth on an iPhone 15 using Depth Anything V2.

[Tim Field @nobbis]

@Kellyv_ai Not built-in. I wrote a few lines to filter the depth image through a colormap.

[Tim Field @nobbis]

A lot better than my depth-from-motion algorithm from 2019.

https://t.co/12eCxTxO7X

[Abound @abound_3d]

Latest depth maps produced by the Abound SDK.

[Tim Field @nobbis]

Paper: https://t.co/YxYGAavw9w by Lihe Yang, @bingyikang et al.
Model: https://t.co/Q4b28bBIvY
App: https://t.co/j82JX1k1TL by @pcuenq

[Tim Field @nobbis]

@coder543 @bingyikang @pcuenq V2 – use the depth-anything-v2 branch

[Tim Field @nobbis]

@gravicle @jon_barron @karanganesan @vokaysh @HaiperGenAI @LumaLabsAI Got it. Haiper restricts unlimited usage by capping concurrent creations to 10. Could be a good option for you guys too.

[Tim Field @nobbis]

@gravicle @jon_barron @karanganesan @vokaysh Curious how you calculate 3-5x cheaper?

@HaiperGenAI is $288.00/yr for 4s videos vs @LumaLabsAI at $287.90/yr for 5s videos.

Both 24fps, Luma is 10% higher resolution, but Haiper is unlimited. (Congrats on the launch BTW.)

[Tim Field @nobbis]

@iwamah1 I believe Area Mode is the new "ignoreBoundingBox" processing option in Object Capture. The documentation says:

"Ignores any bounding box information embedded in the input images and instead returns all possible geometry that can be automatically estimated using the image set."

[Tim Field @nobbis]

@iwamah1 We deliberately keep the price unchanged for continuing Metascan subscribers as a way of thanking early supporters. If you change your subscription, then you'll pay the current price.

App Store developers can increase prices by up to 50% once a year (see https://t.co/HdZxuSANmi)

[Tim Field @nobbis]

@shlykur @Metascan3D It would be great to see – but can't think of how to do that (short of spamming everyone's email.)

Adding a RFS (Request for Scan) feature could be interesting. Not sure how it'd work.

[Tim Field @nobbis]

@bilawalsidhu I bet someone will replace the SHs in 3DGS with a tiny MLP, keep the rest, and say, "Look, it was always a NeRF!"

[Tim Field @nobbis]

"It's just differentiable rendering. Been doing that since Neural Volumes/NeRF in 2019."
- CV folks

"It uses seed & diffuse 3D reconstruction. PatchMatch Stereo showed that in 2011."
- MVS folks

"Hah, it draws Gaussian splats! Try EWA splatting in 2002."
- CG folks

#3DGS

[Tim Field @nobbis]

@bilawalsidhu Turns out NeRFs were just a bunch of overly complicated tricks (positional encoding, space warping, coarse-to-fine, hashtables, view-dependent color with tiny neural nets, cone tracing, etc.) that aren't necessary.

[Tim Field @nobbis]

@rubenfro Strong Terminator 2 vibes.

[Tim Field @nobbis]

@Azadux @BartronPolygon Yeah, 3DGS “the software” must be licensed, but a clean room implementation of the algorithm is fine.

In practice, startups basically ignore that, e.g. we know Luma employees are looking at 3DGS because they were digging into Polycam’s fork of it.

[Tim Field @nobbis]

@gravicle @Azadux Congrats on hiring Jakub recently to get hold of https://t.co/7QWcQFn11t - was wondering who'd scoop up that viewer.

[Tim Field @nobbis]

@antimatter15 @JulienBlanchon Nice - makes it easier. I assumed you were using threads, for some reason.