Real-Time Visualization

Ever wondered how far you can push real-time computer vision using just a lightweight language model and your browser? I just explored smolvlm-realtime-webcam — a fascinating project that captures webcam input, sends it to a local llama.cpp server running SmolVLM (500M params), and gets back live object descriptions from a tiny vision-language model — all in real time. This isn't your typical deep-learning pipeline. It's: Extremely lightweight — no massive GPU needed Browser-based — just HTML + JS Powered by llama.cpp — fast inference on CPU/GPU Hackable — you can prompt it to return structured data like JSON Perfect for edge computing, fast prototyping, or simply geeking out on vision+language systems with minimal overhead. Big shoutout to @ngxson (Xuan-Son Nguyen) and the open-source community behind this. Want to see a llama do object detection from your webcam? Check it out: https://lnkd.in/gHB62wzY #AI #ComputerVision #EdgeAI #llama #SmolVLM #OpenSource #RealTimeAI #llamacpp #MachineLearning #TechDemo

What if you could fly through someone’s brain — and actually watch it think in real time? 🧠 This stunning 3D visualization makes that possible. It shows live brain activity mapped from EEG (electroencephalography) signals onto a realistic 3D model of the human brain. Each color represents a different brainwave frequency — from calm alpha and focused beta, to fast, high-energy gamma rhythms. The golden lines trace the brain’s white matter pathways, and the moving light pulses represent information flowing between regions — the brain communicating with itself in real time. How it’s built The process begins with MRI scans to create a high-resolution 3D model of the brain, skull, and scalp. Then, DTI (Diffusion Tensor Imaging) maps the brain’s wiring — the white matter tracts that connect its regions. Next comes EEG recording, captured using a 64-channel mobile EEG cap. Advanced software pipelines like BCILAB and SIFT clean the data, remove noise, and use mathematical modeling to “source-localize” brain activity — estimating where in the brain each signal originates. They also analyze information flow using a technique called Granger causality, revealing which brain regions are influencing others at any given moment. From Data to Experience All of this is brought to life in Unity, a 3D engine usually used for games. Here, the brain becomes a fully navigable world — you can literally fly through it using a controller and watch live signals flicker and flow. It’s data turned into experience — a fusion of neuroscience, art, and technology that lets us see the living mind at work. Why it matters By merging EEG, MRI, and DTI, researchers can study how the brain’s networks communicate, and how this connectivity changes in conditions like epilepsy, depression, or neurodegenerative diseases. This work also pushes forward brain-computer interface research — paving the way for future technologies that help restore movement, communication, or sensation through brain signals alone. Every flicker of light here represents a thought, a signal, a decision — the brain in motion. 🎥 Video Credits: Dr. Gary Hatlen

This isn't an Unreal Engine walkthrough video, it’s the entire Quixel's Derelict Corridor running live in a web browser, without pixel streaming. Explore the full environment here: https://lnkd.in/dgQ2SHeH A few months ago, we showcased a portion of this scene running in a web browser. Squeezing a single slice of this corridor into a browser was a massive challenge then. Today, we are unleashing the entire facility. Typically, an asset-dense environment of this scale and fidelity requires at least a dedicated NVIDIA RTX A6000 in the cloud just to stream a single instance. Full Derelict Corridor and its visual fidelity has been preserved, all while maintaining a rock-solid framerate on low-end devices and smartphones. Getting here required a hardcore engineering sprint by the Moshpit team. We bypassed the traditional limitations of WebGL by building a 100% GPU-driven pipeline for UnrealTwin: ‣ WebGPU: We’ve moved beyond the limits of WebGL. UnrealTwin now has direct access to the user's GPU hardware via WebGPU, executing blazing-fast Splat sorting using custom compute shaders. ‣ A Custom LOD Pipeline: Standard Gaussian Decimation destroys immersion, it introduces aggressive popping and turns distant geometry into voxelated mush. To preserve Quixel's visual fidelity, we engineered a custom Splat LOD generation pipeline from the ground up. The result is flawless distant rendering without tanking mobile performance. #UnrealTwin is proof that the open web and non-gaming rigs are finally ready for real-time 3D. Have a walk-through and let me know how it runs on your hardware! #UnrealEngine #UE5 #Quixel #GaussianSplatting #3DGS #WebGPU #PlayCanvas #DigitalTwins #Realtime3D #Moshpit #UnrealTwin #TechArt #GameDev

Sharp Monocular View Synthesis in Less Than a Second https://lnkd.in/djBTUjUE Real-time photorealistic view synthesis from a single image. Given a single photograph, regresses the parameters of a 3D Gaussian representation of the depicted scene. Synthesis in less than a second on a standard GPU via a single feedforward pass through a neural network. The synthesized representation is then rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Robust zero-shot generalization. SOTA on multiple datasets while lowering the synthesis time by three orders of magnitude. Code and weights (try it on your images!) at https://lnkd.in/dMjfhnP4 . Project page with videos: https://lnkd.in/dGbuDaht with Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santana, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan Richter

Flying through 3D brain cell electron microscopy data in Unreal Engine with an Xbox controller in real-time: featuring open data from the IARPA MICrONS dataset. The video shows a selection of 250 mouse neurons, originally reconstructed in 3D from electron microscopy data by a large team of researchers from the MICrONS consortium. The rendering is a real-time capture of a 3D scene I set up in the game engine Unreal, using the 3D reconstruction data that has been generously made publicly available by the MICrONS consortium: https://lnkd.in/gDP5rpKv This cortical cubic millimeter data set spans a section of a mouse brain containing about 200,000 cells— so this 250-cell random subset represents less than 1% of the cell density in the original tissue. Each cell mesh is richly detailed, and even this sparse selection of cells is densely packed with data. The dataset has been a great resource for me to stress-test features in Unreal Engine for visualizing dense scientific spatial data. Unreal Engine recently released a new system for handling 3D scenes with dense geometry: Nanite. The idea behind Nanite is for geometry to automatically adapt in detail depending on how far it is from viewer, representing only the amount of detail that is actually perceptible from a given distance. As you get close, the representation becomes more detailed, and as you move away, it is simplified, freeing up resources for more critical parts of the scene. In this scene shown here, this method gives at least a 10-fold improvement in performance, transforming something that is barely workable to a fluid experience. These rendering approaches were originally developed for video games, which are constantly facing demands for increasing depth, scale, and immersion. But we’re facing similar challenges in scientific visualization: an explosion of depth and scale of scientific data and a need to find new ways to represent and engage with that data to make sense of it. ---------------------- References and acknowledgements: The data used for this visualization were produced by a consortium of labs led by members of the Allen Institute for Brain Science, Princeton University, and Baylor College of Medicine (the MICrONS Consortium). I was not involved in studies that generated the data. The dataset is described in the following publication: MICrONs Consortium, J. Alexander Bae, Chi Zhang, et al. Functional connectomics spanning multiple areas of mouse visual cortex. bioRxiv 2021.07.28.454025; doi: 10.1101/2021.07.28.454025 More information about the study, the Microns program, and these data can be found at: https://lnkd.in/gDP5rpKv This post was not sponsored or endorsed by the MICrONS Consortium, or any of its affiliated institutions or researchers. 

In 2008, I had a vision that sounded simple but felt impossible. I wanted to see everything happening at the airport, in real time. From the moment a guest arrives at the terminal, to the time it takes to get an aircraft ready for its next flight, baggage handling, safety checks, security clearances, and even external factors like weather and #traffic. Fast forward to today, and that vision is a reality: Real-Time #DXB. This dashboard is an integrated platform running across 10+ oneDXB service partner control centres, bringing together data from over 50 different systems into the cloud to create a live “digital twin” of airport operations. Every second, it visualises hundreds of thousands of data points, from flight movements to baggage flows, passenger touchpoints to airside activity, giving us a full picture of the airport’s pulse. The impact is profound. By eliminating silos, it keeps all teams aware of developing situations, helps anticipate disruptions before they become problems, and drives collaboration between partners. Whether you work in baggage, security, ground handling, or terminal operations, you see the same truth and act on it in sync. Yes, this is our system, but also our way of working.  When all our partners see the same truth, we move faster, smarter, and together. And, in an environment where every second counts, that changes everything.

🚀 Real-time BIM Visualization: AI + Open IFC vs. Traditional Tools I just completed an experiment that challenges how we think about computational design workflows. The Challenge: Generate a 34-level tower (7×5 bay grid) where each cell contains unique architectural, MEP, and structural data from CSV files. Then apply a simplex noise algorithm to dynamically hide/show cells every second, creating an animated visualization of the building systems. The Result: Using AI and Fragments by Open IFC, I built this in under an hour. It renders at 60 FPS with real-time updates every second, complete with dynamic sun movement and sharp shadows. The Question: Can you do this in Revit + Dynamo? How long would it take to set up? How long to render each frame? If Fragments and open-source IFC tools are faster, lighter, and more flexible than Revit's ecosystem, #WHY are we still locked into proprietary workflows? The AEC industry is at a crossroads. Real-time visualization, procedural generation, and web-based collaboration are no longer "nice to have" – they're becoming the standard. Time to rethink our tools? 🤔 #BIM #ComputationalDesign #OpenIFC #Revit #Dynamo #AECTech #DigitalTwin #GenerativeDesign #WebGL #ThreeJS #BuildingInformation #ConstructionTech #ArchTech #Innovation #OpenSource #RealTimeRendering #Revit #Autodesk

You can monitor 𝗵𝗼𝘀𝗽𝗶𝘁𝗮𝗹 𝗯𝗲𝗱 𝗼𝗰𝗰𝘂𝗽𝗮𝗻𝗰𝘆 𝗶𝗻 𝗿𝗲𝗮𝗹 𝘁𝗶𝗺𝗲 by using 𝗦𝘆𝗻𝗼𝗽𝘁𝗶𝗰 𝗣𝗮𝗻𝗲𝗹 in Power BI. In this example, the report helps staff instantly see which beds are free, occupied, or require special attention, directly from Power BI and without building a custom application. The solution works on tablets, relies on 𝗗𝗶𝗿𝗲𝗰𝘁𝗤𝘂𝗲𝗿𝘆 for up-to-date information, and uses 𝗣𝗼𝘄𝗲𝗿 𝗕𝗜 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 to manage access across different hospital areas. The full case study explains how the floor-plan map was created, how the icons and statuses work, and why this approach is efficient even with frequently changing datasets. 𝗜𝗻𝘀𝗶𝗱𝗲 𝘁𝗵𝗲 𝗰𝗮𝘀𝗲 𝘀𝘁𝘂𝗱𝘆, 𝘆𝗼𝘂 𝘄𝗶𝗹𝗹 𝗳𝗶𝗻𝗱: – How the floor-plan map was designed – How real-time status is displayed through DirectQuery – How to represent availability, gender, and infectious conditions – How the model is structured in Power BI – Practical guidance to build similar solutions 𝗙𝘂𝗹𝗹 𝗰𝗮𝘀𝗲 𝘀𝘁𝘂𝗱𝘆 𝗮𝗻𝗱 𝗶𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗱𝗲𝘁𝗮𝗶𝗹𝘀 https://lnkd.in/deT8jeQt 𝗧𝗿𝘆 𝗦𝘆𝗻𝗼𝗽𝘁𝗶𝗰 𝗣𝗮𝗻𝗲𝗹 https://lnkd.in/dEC-jy8M You can adopt a similar solution in similar cases where you want to display near-real-time updates for map-based visualizations. 𝗦𝗵𝗮𝗿𝗲 𝘁𝗵𝗶𝘀 𝗽𝗼𝘀𝘁 with teams or partners who could benefit!

Real-Time UI: https://lnkd.in/dNbmGcX8 "A prototype is worth 1000 meetings." But what if the meeting _is_ the prototype? That’s the spirit of an idea I’m calling “Real-time UI” (the name of which I gave next-to-no thought, so forgive me). The tools and technologies now exist to generate UI in realtime, making it possible to convert a conversation into a working digital thing. In this video, I introduce the concept to TJ Pitre and Ian Frost , and we talk about the possibilities and ramifications of generating UI in realtime, as well as speaking to the infinite creative potential of using AI & design systems together, as we are covering in our course: https://lnkd.in/eG5h8uaP https://lnkd.in/dubfHuCn As I see it, real-time UI can help accomplish a number of things: ◉ Visualize UI components in real-time – surfacing design system components immediately as they’re referenced in conversation (design systems are a shared language!) ◉ Visualize product design in real-time. Make abstract ideas real as soon as the words exit your mouth, and use the working prototype as a wet ball of clay the team can sculpt together over the course of a conversation. ◉ Wield your design system’s infrastructure to make realistic things. The spirit is to have the conversation and infrastructure tuned to your specific team’s context. Create prototypes that are built using your organization’s best practices rather than whatever AI decides to randomly generate. ◉ Minimize the friction involved in making prototypes ◉ A visual accompaniment to a conversation can help teams unlock new ideas, expose weak spots, explore opportunities, and iterate collaboratively ◉ Open the door to a more participatory design process. Diversity is critical to success, and it’s so important to make sure that digital products represent the best thinking from different disciplines & perspectives at a company. Historically, the design process was prohibitive to people who weren’t skilled in the mechanical aspects of creating designs & code. This is no longer the case. Of course professional designers or developers are still necessary (now more than ever!) to produce great results, but there’s now an opportunity to create more democratic, collaborative, participatory design workflows. If you're interested in exploring the future of using design systems and AI together, we'd love it if you joined our community by preordering our AI & Design Systems course! #ai #designsystems #ux #uxdesign #frontend #prototyping #design #process #workflow #collaboration

A Real-Time Face Encoding Visualizer. how a Ai sees us with the help of cameras. Ever wondered how an AI "sees" your face? This system doesn't just detect features; it transforms them into a 128-dimensional numerical descriptor (encoding) and renders it live using a Matrix-inspired visualization. Key Features: ✅ 100% Browser-Based: Built with Vanilla HTML/CSS/JS and face-api.js. ✅ Edge Computing: No backend, no API calls. All neural network inference happens locally on the device for maximum privacy and speed. ✅ Numerical Rendering: My face is reconstructed as a wall of real-time encoding values—turning biological features into digital signatures. ✅ Premium UI: Dark mode aesthetics with glassmorphism and a "Face-as-Numbers" canvas. This was a fun deep dive into WebRTC, neural descriptors, and creative coding. It’s a literal look at the intersection of computer vision and data art! What do you think? Digital twin or just a bunch of numbers? 🤔 Github:https://lnkd.in/daQ_XgJT #ComputerVision #ArtificialIntelligence #WebDevelopment #CodingProject #DataScience #FaceDetection #JavaScript #NeuralNetworks #CreativeCoding #TechInnovation