SAM 3D: 3Dfy Anything in Images

Kari Jaaskelainen

21 Nov 2025 — 1 min read

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

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added