SAM 3D: 3Dfy Anything in Images
Meet SAM 3D: a generative model that 3Dfies anything you capture. From a single photo, it rebuilds an object's geometry, texture, and layout in the scene. It is built for messy, natural images with clutter and occlusion, using context cues to stay visually grounded.
How it works
- Human + model-in-the-loop pipeline labels object shape, texture, and pose, scaling up visually grounded 3D data.
- Multi-stage training: synthetic pretraining followed by real-world alignment, breaking the 3D data barrier.
- Learns to infer 3D even when parts are hidden by leveraging surrounding scene cues.
Results
On real-world objects and scenes, SAM 3D outperforms recent methods in human preference tests by at least 5:1, producing cleaner geometry and more faithful textures and poses.
What’s next
Releasing soon: code, model weights, an online demo, and a challenging benchmark for in-the-wild 3D reconstruction. Learn more: https://arxiv.org/abs/2511.16624v1
Paper: https://arxiv.org/abs/2511.16624v1
Register: https://www.AiFeta.com
#SAM3D #3D #3DReconstruction #ComputerVision #GenerativeAI #AR #VR #Robotics #arXiv
