Cameron Smith

@jadroy2 make one for robot arms too 🙏

introducing humanoid index i wanted one place i could browse n compare current humanoids, so i created one crafted with 🫶🫶🫶 and through yapping an absurd amount to claude code for a couple of months

IMO this is a much needed quality-of-life upgrade to the 3D-aware robotics stack for the new paradigm of vision-based robot control Thanks as always to the great mentor team of @basilevanh @vitorguizilini @yuewang314

I've found it incredibly useful in my recent experiments -- camera pose and intrinsics from a single image and even moving camera stream, as well as for really easy one-second robot re-calibration

Inferring a robot’s 3D state (robot↔camera pose + joint angles / link poses) is still weirdly clunky Introducing Fiducial Exoskeletons: Image-Centric Robot State Estimation! cameronosmith.github.io/fiducial_exosk… FidEx makes it fast + robust from a single image 🧵

Introducing the USC Physical Superintelligence (PSI) Lab (psi-lab.ai). We are rebranding to better reflect our current focus. From here on out, we are tackling one thing: solving robotics and physical intelligence with every model, every bug, and every line of code. And yes, we are hiring at all levels, especially PhDs in this cycle and potential PostDocs who are excited about robotics. We hope you can join us in this journey! 1/9

[Hiring!] I am hiring multiple PhDs @CSatUSC @USCViterbi for this cycle. If you're interested in scene representations, neural simulation, generative AI, and robotics, feel free to mention my name in your application (no need to email). For USC masters/undergrads who're interested in our research, feel free to fill in this form forms.gle/RerZfDqCqmCj8A….

I am looking for graduate students for my new lab at the University of Cambridge! Join me to understand and build models of visual perception.

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! cameronosmith.github.io/flowmap/ IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

I quit PhD (for a day) and opened a boba shop at @MIT - Generative Boba! It’s a huge success - right next to our office so all the AI researchers are enjoying it. Checkout our boba diffusion algorithm in the poster to understand why boba generation is so important to @MIT_CSAIL !

Introducing pixelSplat: feed-forward Gaussian splats from image pairs! Led by @DavidCharatan and @sizhe_lester_li, collaborating with @taiyasaki! We propose a memory-efficient, fast and editable alternative to pixelNeRF based on 3D Gaussian Splatting! davidcharatan.com/pixelsplat/ 1/n

I am presenting my paper “RaMP: Self-Supervised Reinforcement Learning that Transfers using Random Features” at poster 1427 from 5-7pm at Neurips 2023! Don’t miss it! Website: buoyancy99.github.io/ramp-rl/

How can we learn to generate 3D scenes directly with diffusion models if we only have images, no ground-truth 3d scenes? Ayush, Tianwei and George will tell you at our poster “diffusion with Forward Models”, #202!

Placing the camera on top of a pet is one of the coolest applications of NeRFs I've seen

Check out “Diffusion with Forward Models”. We learn to sample realistic 3D scenes from a single input image. Our models are trained on videos and do not require 3D training data! …ffusion-with-forward-models.github.io (1/n)

One of the coolest 3D computer vision papers, ever!