# H3M

> H3M is an award-winning AI and immersive technology studio building spatial computing and augmented reality experiences, and the creator of Portals, the no-code AR builder.

H3M (h3m.ai) is a creative technology company working at the intersection of artificial intelligence, immersive experiences, spatial computing and augmented reality (AR). H3M Lab produces award-winning brand experiences (Cannes Lions Gold 2023 for Naafiri with Riot Games; Clio Gold 2024 for Google Cloud at the Las Vegas Sphere; Telly Gold 2024 for Paramount's Yellowstone at the Las Vegas Sphere). Portals is H3M's AI-powered, no-code spatial computing app for building and sharing AR worlds using Gaussian splatting, body tracking, geolocation, 3D painting and generative AI.

Contact: hello@h3m.ai

## Pages

- [H3M | AI Immersive Studio for Spatial Computing & Augmented Reality](https://h3m.ai/): H3M is an award-winning AI and immersive studio building spatial computing and augmented reality experiences, plus Portals, the no-code AR creation platform.
- [H3M Lab | Award-Winning Immersive Experience & AR Studio](https://h3m.ai/lab): H3M Lab partners with global brands on Cannes Lions and Clio-winning immersive experiences built with generative AI, augmented reality, XR and spatial computing.
- [Projects | Immersive AR, AI & Spatial Computing Case Studies](https://h3m.ai/projects): Explore H3M’s immersive work: AI cinematics, augmented reality retail, Gaussian splat environments and spatial experiences for Riot Games, Ubisoft and more.
- [Portals | AI-Powered No-Code AR & Spatial Computing Builder](https://h3m.ai/portals): Portals is H3M’s AI-powered spatial computing app. Build augmented reality worlds with Gaussian splats, body tracking, geolocation and real-time VFX, no code needed.
- [No-Code AR Builder | Create Augmented Reality Experiences with AI](https://h3m.ai/no-code-ar-builder): Build professional augmented reality experiences without code. H3M Portals uses AI, Gaussian splatting and WebXR to create, publish and share immersive AR.
- [Research | AI, Spatial Computing & Augmented Reality Insights](https://h3m.ai/research): H3M research on generative AI, spatial computing, augmented reality, Gaussian splatting, neural radiance fields and the future of immersive media.
- [Identity | Your Portals Spatial Profile, Sigil & XP](https://h3m.ai/identity): Your Portals Identity is your passport to the spatial web. Claim your sigil, track XP and unlock new reality layers in H3M’s immersive AR platform.
- [Fuel Staking & XP Rewards | Portals by H3M](https://h3m.ai/blockchain): Stake Fuel, boost XP and earn rewards inside Portals, H3M’s AI-powered spatial computing and augmented reality platform.
- [Development Log | Portals Build Updates](https://h3m.ai/development-log): Live development updates from the H3M team building Portals, the AI-powered augmented reality and spatial computing app.
- [Privacy Policy](https://h3m.ai/privacy-policy): How H3M collects, uses and protects your information across h3m.ai and the Portals app.
- [Terms & Conditions](https://h3m.ai/terms-and-conditions): Terms and conditions for using h3m.ai, Portals and other H3M services.

## Research

- [Persistent AR: Stateful Spatial Worlds, Built on a Phone](https://h3m.ai/research/persistent-ar-stateful-spatial-worlds-on-a-phone): What would it take for anyone to build a spatial world on a phone and find it exactly where they left it? Inside Portals' approach to persistent augmented reality: creation without 3D skills, scenes stored as intent rather than geometry, and real-time Gaussian splats on edge devices.
- [Text-to-World Generation: Designed Worlds from a Sentence](https://h3m.ai/research/text-to-world-generation-designed-worlds-from-a-sentence): Can a sentence compose a 3D world to an art director's standard? How H3M's worldgen system turns a prompt into a lit, finished space: looks stored as data, a catalogue of 1,576 reusable components, and an AI critic whose feedback became 45 art-direction rules.
- [Semantic Memory: AI That Cites Its Source](https://h3m.ai/research/semantic-memory-ai-that-cites-its-source): Language models rebuild meaning from raw text on every query, and their answers drift from their sources.
- [Latent Compute: Devices That Learn What They Can Sense](https://h3m.ai/research/latent-compute-devices-that-learn-what-they-can-sense): Phones and laptops carry sensors and telemetry that operating systems routinely average away.
- [The Immediacy of Imagination: AI Forges Living Worlds](https://h3m.ai/research/the-immediacy-of-imagination-ai-forges-living-worlds): The accelerating pace of AI image generation is collapsing the distance between a spark of an idea and a fully realized spatial experience.
- [The Living Canvas: AI, Wearables, and the Emergence of a Spatial Economy](https://h3m.ai/research/the-living-canvas-ai-wearables-and-the-emergence-of-a-spatial-economy): A new economic paradigm is unfolding, driven by the convergence of AI's generative power and spatial computing's ability to merge digital with physical.
- [The Emergence of Living Worlds: Where AI Imagination Steps into Reality](https://h3m.ai/research/the-emergence-of-living-worlds-where-ai-imagination-steps-into-reality): As AI models advance from static image generation to dynamic, temporal video, they're not just creating content to be watched.
- [The Illumination of Imagination: How AI Lights the Path for Worlds in Reality](https://h3m.ai/research/the-illumination-of-imagination-how-ai-lights-the-path-for-worlds-in-reality): We stand at the precipice of a new era where the imagined and the real seamlessly merge.
- [The Dawn of Instant Reality and the Future of Spatial Creation](https://h3m.ai/research/the-dawn-of-instant-reality-and-the-future-of-spatial-creation): Tencent's Hunyuan3D-2 represents a significant leap in text-to-3D generation, offering rapid, high-fidelity asset creation.
- [Sharpening Perception for Truly Immersive Spatial Computing](https://h3m.ai/research/sharpening-perception-for-truly-immersive-spatial-computing): We delve into BiRefNet, a state-of-the-art salient object detection model.
- [Unlocking High-Fidelity 3D Human Mesh Recovery with Diffusion Models](https://h3m.ai/research/unlocking-high-fidelity-3d-human-mesh-recovery-with-diffusion-models): This article explores ScoreHMR, a cutting-edge implementation of 3D Human Mesh Recovery (HMR) utilizing score-based diffusion models to infer 3D human shape and pose from 2D images.
- [The Dawn of Scalable Zero-Shot Image-to-Video Synthesis](https://h3m.ai/research/the-dawn-of-scalable-zero-shot-image-to-video-synthesis): MimicMotion represents a significant breakthrough in AI-driven video generation, leveraging essential diffusion models to achieve scalable, zero-shot image-to-video synthesis.
- [Pioneering Dynamic Human Reconstruction with Neural Radiance Fields for Immersive Futures](https://h3m.ai/research/pioneering-dynamic-human-reconstruction-with-neural-radiance-fields-for-immersive-futures): GVHMR (Generative Volumetric Human Mesh Reconstruction) represents a significant leap in capturing and recreating dynamic human forms.
- [Democratizing High-Fidelity 3D Avatar Generation with AI](https://h3m.ai/research/democratizing-high-fidelity-3d-avatar-generation-with-ai): ExAvatar-jupyter represents a significant leap in accessible 3D avatar creation, leveraging advanced AI models to generate realistic digital humans from simple text prompts or single 2D images.
- [Democratizing Dynamic Narratives: Unpacking StableAnimator-Jupyter's Role in AI-Driven Animation](https://h3m.ai/research/democratizing-dynamic-narratives-unpacking-stableanimator-jupyter-s-role-in-ai-driven-animation): StableAnimator-Jupyter represents a significant leap in accessible AI video generation, transforming complex Stable Diffusion models into a user-friendly animation platform via Google Colab.
- [Real-Time Depth Reconstruction from Gaussian Splats: Advancing Spatial Computing and Immersive Experiences](https://h3m.ai/research/real-time-depth-reconstruction-from-gaussian-splats-advancing-spatial-computing-and-immersive-experiences): Gaussian Splatting (3DGS) has revolutionized real-time photorealistic rendering, but its inherent structure also presents a potent, albeit less explored, pathway for real-time depth map extraction.
- [Trellis Tiled Diffusion: Unlocking High-Resolution Generative AI Through Spatial Optimization](https://h3m.ai/research/trellis-tiled-diffusion-unlocking-high-resolution-generative-ai-through-spatial-optimization): Trellis Tiled Diffusion, as demonstrated by the `trellis-tost` project, introduces a sophisticated method for generating ultra-high-resolution images with Stable Diffusion XL by intelligently breaking down and reassembling latent space tiles.
- [HunyuanWorld-Voyager: Pioneering AI-Driven 3D World Generation for the Spatial Web](https://h3m.ai/research/hunyuanworld-voyager-pioneering-ai-driven-3d-world-generation-for-the-spatial-web): Tencent Hunyuan's 'HunyuanWorld-Voyager' represents a significant breakthrough in AI-powered 3D content creation, enabling the rapid generation of complex, immersive virtual environments from simple text or image prompts.