Excited to share this dataset with registered aerial and ground images with dense geometry and correspondence supervision. Please see Khiem’s thread for some cool applications this enables!

Generalist manipulation policies often struggle out-of-the-box in unseen scenarios. Our work DemoDiffusion allows guiding a pre-trained diffusion policy (e.g. Pi-0) via a single human demonstration to perform new tasks in new environments. Work led by Sungjae Park and Homanga Bharadhwaj

Check out our #ICCV2025 paper, LightSwitch, that learns a multi-view relighting diffusion model. This allows efficiently relighting any number of input images and also obtaining relit 3D assets in just a couple minutes. Project page: yehonathanlitman.github.io/light_switch/

It was a pleasure working with Homanga Bharadhwaj at CMU, and you should definitely apply to be a part of his group if you want to be at the frontier of research in building generalizable robots

3Dfy anything from a single image! Very thrilled to announce SAM 3D. From an input image, select any object you want, 3Dfy it! Blog: ai.meta.com/blog/sam-3d/ Demo: aidemos.meta.com/segment-anythi…