Meet Mon3tr: Lifelike 3D Telepresence from One Camera

Kari Jaaskelainen

13 Jan 2026 — 1 min read

Imagine joining a meeting as a lifelike 3D hologram—no studio rig, just your phone or laptop camera. Mon3tr makes this possible.

How it works: Mon3tr builds your personal 3D avatar once (offline) from multi-view photos. During calls, a single RGB camera tracks your body and face to drive that avatar in real time. Only compact motion-and-appearance features are sent—under 0.2 Mbps over WebRTC—so it stays smooth even on spotty networks.

On the receiver (e.g., Meta Quest 3), a lightweight “Gaussian” renderer—think a cloud of tiny 3D dots—fine-tunes the pre-built avatar on the fly, delivering photorealistic motion and expressions at about 60 FPS.

Results: over 1000× less bandwidth than point-cloud streaming, about 80 ms end-to-end latency, and high visual quality (>28 dB PSNR) across diverse scenes—while running from a single camera.

Demos: https://mon3tr3d.github.io

Paper: https://arxiv.org/abs/2601.07518v1

Register: https://www.AiFeta.com

#AR #VR #Telepresence #3D #AI #ComputerVision #XR #WebRTC #MetaQuest #GaussianSplatting #Monocular #Holograms

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

Read more

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

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

AI that explains itself—by following the science

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