Siddharth Choudhary

Presenting MeasureNet, a computer vision based model for precise Waist-to-Hip Ratio (WHR) measurement. Joint work with Ganesh Iyer (@__epiception__ ), Brandon Smith, Jinjin Li, Mark Sippel, Antonio Criminisi and Steven B. Heymsfield. (1/8)

@iamgrigorev Did you also try MuonH? It does show benefit in small scale runs for me but I haven't scaled it up.

lol there’s been so many optimizers this week I can’t test them all. (btw Aurora doesnt work on large scale)

Checkout Alessandro's work on reducing VLM hallucination on Thursday! #CVPR2024

We present SplatArmor, a fully articulated Gaussian splatting model for human avatars. Our model includes both rigid and non-rigid skinning components, and a Neural Color Field for implicit color regularization. Project page: jenaroh.it/splatarmor

With 1200 participants, we've validated the MeasureNet app's accuracy and reliability. We're bridging the gap between clinical measurements and at-home assessments, making WHR monitoring more accessible for everyone. (8/8)

In order to solve this issue, our team developed MeasureNet that accurately measures WHR and other key body metrics using computer vision. Say goodbye to inconsistent self-measurements! (7/8)

Presenting MeasureNet, a computer vision based model for precise Waist-to-Hip Ratio (WHR) measurement. Joint work with Ganesh Iyer (@__epiception__ ), Brandon Smith, Jinjin Li, Mark Sippel, Antonio Criminisi and Steven B. Heymsfield. (1/8)

rebuttal.pdf uploaded ✅ rebuttal.mp3 uploaded ✅ Whats more fun than writing a rebuttal? Making an AI-generated diss track for the #ICCV2023 reviewers (ft. @atemyipod ) it's amazing how effortless this is to make #iccv soundcloud.com/rohit-kumar-je…

@tcies @davsca1 @CSProfKGD @MichaelBloesch @mapo1 @SattlerTorsten Congratulations Titus! It was great working with you :)

Thesis submitted! Thanks to @davsca1 and my colleagues at RPG for great 5 years, to @siddharth0708, @CSProfKGD, @MichaelBloesch & Andreas Ziegler for co-authoring the core papers, and to @mapo1 and @SattlerTorsten for agreeing to review! 5 years of research on a single screen:

My Ph.D advisor's startup @hellorobotinc comes out of stealth mode :-)

🎉 Introducing... Methods! We are now tracking 730+ building blocks of machine learning: optimizers, activations, attention layers, convolutions and much more! Compare usage over time and explore papers from a new perspective. Browse the catalogue here: paperswithcode.com/methods

This graph is really eye-opening.

@olshansky @pavelociraptor Which company did you use? I'm looking for a standing desk as well.

@pavelociraptor Got it off a liquidation company in the Bay Area :)

A new experimental feature in the @magicleap OS 0.98.10 update; Found Objects. Developers can access this information which makes me want to make a bridge-building game across my living room. #magicleapdevs.

@tokufxug thanks for sharing this exciting experimental platform feature! a team of engineers and designers did a lot of work to bring it to light in the latest release. here’s another video of it in action.

Excited about releasing a 3d object recognition feature with the latest update. The algorithm is designed with scalability, multi-user and persistence scenarios in mind.