🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Generate high quality textures with single mesh LDMs! #CVPR2024 Our *intrinsic* 3D diffusion models, trained on a single mesh, can generate texture variations, perform inpainting, and even transfer textures to different shapes. single-mesh-diffusion.github.io w/Tommy Mitchel & Carlos Esteves

Announcing (fashionably late) our #CVPR2024 paper on GenAI detection! with Avneesh Sud, Thomas Leung, and Ben Usman Fake-Inversion: Learning to Detect Images from Unseen Models by Inverting Stable Diffusion fake-inversion.github.io More info in 🧵 1/7

Introducing Neural Isometries where we show how to exploit equivariant ML even for transformations that are “nasty”, e.g. non-compact, projective, nonlinear, or not even a group action! arxiv.org/abs/2405.19296 Collab w/ the amazing Tommy Mitchel Tommy Mitchel and Mike Taylor! 1/n

At #CVPR2024, I will give a talk about "Geometric Deep Learning for Weather" at the Equivariant Vision workshop Tue 2pm equivision.github.io, and I'll present a poster on Single Mesh Diffusion Wed 5pm single-mesh-diffusion.github.io w/ Tommy Mitchel and Ameesh Makadia. Hope to see you there!

Talking at the INR for vision workshop in a moment - summit 335/336!

Our paper "Zero-Shot Image Feature Consensus with Deep Functional Maps" is accepted at #ECCV2024! European Conference on Computer Vision #ECCV2026 Want better image correspondences with noisy and inaccurate features? Let's go to the spectral space with Laplacian eigenfunctions! ArXiv: arxiv.org/abs/2403.12038

We have released the code for our paper "Neural Isometries"! All the links here: scenerepresentations.org/publications/n… Amazing work by Tommy Mitchel :)

If you are interested in geometry processing, I highly recommend applying to Silvia's lab - she is brilliant and kind and will be an amazing adviser :)

Introducing Neural Jacobian Fields, robot 3D kinematic models learned only from vision! They can model & control robots from just a single RGB camera, even those w/ intractable kinematics & no embedded sensors such as soft, 3D-printed pneumatic hands! sizhe-li.github.io/publication/ne… 1/n

What roles can "Geometry" play nowadays in this large model era? What are the current difficulties and future opportunities? Check out ECCV 2024 workshop "Geometry in Large Model Era"! 📍 Sep. 30 PM, Brown 3 🔗 geo-lme.github.io

A thread and video by MIT CSAIL about our Diffusion Forcing paper!

I'll be recruiting PhD and MSc students through Mila - consider applying if you want to work at the intersection of machine learning and 3D geometry!

Really happy to see this study! Always wanted to do something like this myself, if only to support calming words to grad students: current-gen generative models have nothing to do with intelligence, and AI research remains fascinating and unsolved!

Meet us and chat with us about symmetry discovery at today's afternoon poster session at NeurIPS, East Exhibit Hall A-C #2110, where we will be presenting Neural Isometries! Tommy Mitchel