正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

A guy from China just built a system that reshapes thousands of glowing particles into a jellyfish, a dragon, a statue, and a samurai. Just by moving his hands in front of a camera. Just a webcam reading his hand position. Every particle recalculates in real time. 60 frames... show more

Vaibhav Sisinty

169,951 subscribers

18,334 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

This guy built a visual scanner that reads 468 points on his face and 42 points on his hands from a regular webcam and turns them into a cloud of thousands of particles right between his palms. Inside, MediaPipe and TouchDesigner are linked: the first captures hands and face from the webcam with high accuracy, the second turns those coordinates into a live plane and feeds it into a POP system that instantly generates a swarm of particles in the shape of a head. No studio, no render farmer, no VR headset. Just a laptop, a webcam, and 1 TouchDesigner session. And traditional VJ studios keep teams of 5 people on a setup with lighting, custom hardware, and commercial plugins, while his expenses are only a TouchDesigner subscription and a regular USB camera. One laptop runs MediaPipe and TouchDesigner simultaneously, holds the camera stream at 60 FPS without drops, and in parallel processes 468 face points + 21 points on each hand. The camera captures frame after frame, MediaPipe in real time sends TouchDesigner the finger coordinates and face geometry, and the POP operator inside the engine translates those numbers into thousands of particle points with colors from bright pink to gold. This setup immediately defines the role of the tool and the limits of its autonomy. It knows where the fingertips are at every moment of the frame. It knows how to read the face geometry at any angle to the camera. It knows how to draw a swarm of particles between them with the right color and contour. → MediaPipe pulls 468 points from the face and 21 points from each hand, 60 times per second → TouchDesigner receives those coordinates, builds a virtual rectangle between the fingertips, and feeds it into the POP system → POP generates thousands of particle points in the shape of a head, coloring them in a gradient from bright pink to gold → The HUD layer adds green corners and a blue neon frame, styling the image like an AR interface → All layers assemble into 1 real-time frame that projects back onto the video in the camera window → The final image is recorded to a file or broadcast to a projector for a live installation And only when the guy spreads his hands wider does the plane between the palms stretch; brings them together, it narrows. Otherwise the system runs on its own. And when he moves from his home room to a concert hall, the same laptop with the same webcam launches the same TouchDesigner session in just 5 minutes, without reconfiguration, without a new team, and without a single line of new code. In his work setup there is no studio of his own and no team for assembly. On the desk sits a laptop with a webcam, on top run MediaPipe and TouchDesigner with POP operators, and the same setup through a USB camera moves to any concert without a new configuration. Out of everything I have seen this year, this is the cleanest Creative Coding setup on 1 laptop: 0 render farms, 0 studio lighting, and between them 3 libraries, thousands of particle points, and 1 webcam.

This guy built a visual scanner that reads 468 points on his face and 42 points on his hands from a regular webcam and turns them into a cloud of thousands of particles right between his palms. Inside, MediaPipe and TouchDesigner are linked: the first captures hands and face from the webcam with high accuracy, the second turns those coordinates into a live plane and feeds it into a POP system that instantly generates a swarm of particles in the shape of a head. No studio, no render farmer, no VR headset. Just a laptop, a webcam, and 1 TouchDesigner session. And traditional VJ studios keep teams of 5 people on a setup with lighting, custom hardware, and commercial plugins, while his expenses are only a TouchDesigner subscription and a regular USB camera. One laptop runs MediaPipe and TouchDesigner simultaneously, holds the camera stream at 60 FPS without drops, and in parallel processes 468 face points + 21 points on each hand. The camera captures frame after frame, MediaPipe in real time sends TouchDesigner the finger coordinates and face geometry, and the POP operator inside the engine translates those numbers into thousands of particle points with colors from bright pink to gold. This setup immediately defines the role of the tool and the limits of its autonomy. It knows where the fingertips are at every moment of the frame. It knows how to read the face geometry at any angle to the camera. It knows how to draw a swarm of particles between them with the right color and contour. → MediaPipe pulls 468 points from the face and 21 points from each hand, 60 times per second → TouchDesigner receives those coordinates, builds a virtual rectangle between the fingertips, and feeds it into the POP system → POP generates thousands of particle points in the shape of a head, coloring them in a gradient from bright pink to gold → The HUD layer adds green corners and a blue neon frame, styling the image like an AR interface → All layers assemble into 1 real-time frame that projects back onto the video in the camera window → The final image is recorded to a file or broadcast to a projector for a live installation And only when the guy spreads his hands wider does the plane between the palms stretch; brings them together, it narrows. Otherwise the system runs on its own. And when he moves from his home room to a concert hall, the same laptop with the same webcam launches the same TouchDesigner session in just 5 minutes, without reconfiguration, without a new team, and without a single line of new code. In his work setup there is no studio of his own and no team for assembly. On the desk sits a laptop with a webcam, on top run MediaPipe and TouchDesigner with POP operators, and the same setup through a USB camera moves to any concert without a new configuration. Out of everything I have seen this year, this is the cleanest Creative Coding setup on 1 laptop: 0 render farms, 0 studio lighting, and between them 3 libraries, thousands of particle points, and 1 webcam.

Blaze

38,242 次观看 • 5 个月前

a Vietnamese AI engineer just built a real-time system that counts objects moving down a conveyor belt. it runs on ultralytics' objectcounter. train a detector, define the region you care about, and it handles the rest. works for anything on a line, parts, packages, produce. the clever bit: instead of hand-labeling thousands of frames, he took a single frame, pre-annotated it with meta's segment anything (sam-2, built into ultralytics), and trained yolo11-nano on just that. one annotated frame, and it tracks objects accurately across the entire video.

a Vietnamese AI engineer just built a real-time system that counts objects moving down a conveyor belt. it runs on ultralytics' objectcounter. train a detector, define the region you care about, and it handles the rest. works for anything on a line, parts, packages, produce. the clever bit: instead of hand-labeling thousands of frames, he took a single frame, pre-annotated it with meta's segment anything (sam-2, built into ultralytics), and trained yolo11-nano on just that. one annotated frame, and it tracks objects accurately across the entire video.

Oliver Prompts

29,786 次观看 • 2 个月前

China just dropped an open source model that turns any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the reply

China just dropped an open source model that turns any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the reply

savip.

105,419 次观看 • 2 个月前

This guy built something that changes your face in real time using hand gestures. And it looks insane. 🤯 Viet Nguyen, a Senior AI engineer, built a personal project that transforms your face into 16 different visual styles. Van Gogh. Neon. Anime. Pop art. Graffiti. All triggered by just moving your hand. Open your hand. AI reads the gesture. Your face transforms into a completely different art style. Almost instantly. 16 styles. One hand movement. Zero clicks. The wild part: he built this as a side project. Not a product. Not a startup. Just one engineer combining two existing tools in a way nobody had thought to before. This is what personal projects look like in 2026.

This guy built something that changes your face in real time using hand gestures. And it looks insane. 🤯 Viet Nguyen, a Senior AI engineer, built a personal project that transforms your face into 16 different visual styles. Van Gogh. Neon. Anime. Pop art. Graffiti. All triggered by just moving your hand. Open your hand. AI reads the gesture. Your face transforms into a completely different art style. Almost instantly. 16 styles. One hand movement. Zero clicks. The wild part: he built this as a side project. Not a product. Not a startup. Just one engineer combining two existing tools in a way nobody had thought to before. This is what personal projects look like in 2026.

Vaibhav Sisinty

25,242 次观看 • 3 个月前

THIS $2 AI VISUAL SETUP JUST MADE A $250/MONTH CREATIVE STACK LOOK STUPID he moves his hand, the particles react, and the whole scene updates in real time. no cloud render farm, no paid visual API, no expensive plugin chain quietly eating money every month most people still think ai visuals require a stack of $39 tools, $89 subscriptions, and constant API usage. but here the loop is simple: TouchDesigner handles the visuals, a local model handles the logic, and the laptop does the rest the important part is not that the particles look cool. the important part is that the “brain” behind the visual no longer has to live on someone else’s server once that moves local, the monthly bill falls off a cliff this is probably how a lot of small studios start building visuals soon: not by renting 6 tools forever, but by owning one system that runs almost for free

THIS $2 AI VISUAL SETUP JUST MADE A $250/MONTH CREATIVE STACK LOOK STUPID he moves his hand, the particles react, and the whole scene updates in real time. no cloud render farm, no paid visual API, no expensive plugin chain quietly eating money every month most people still think ai visuals require a stack of $39 tools, $89 subscriptions, and constant API usage. but here the loop is simple: TouchDesigner handles the visuals, a local model handles the logic, and the laptop does the rest the important part is not that the particles look cool. the important part is that the “brain” behind the visual no longer has to live on someone else’s server once that moves local, the monthly bill falls off a cliff this is probably how a lot of small studios start building visuals soon: not by renting 6 tools forever, but by owning one system that runs almost for free

Ridark

15,948 次观看 • 4 个月前

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the system to maintain a consistent identity for each pothole across frames rather than treating every detection as a new, isolated event.

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the system to maintain a consistent identity for each pothole across frames rather than treating every detection as a new, isolated event.

Ryohei Sasaki@engineer

102,347 次观看 • 1 个月前

As a Komodo dragon charges, he jumps into the back of his vehicle and drives off just in time.

As a Komodo dragon charges, he jumps into the back of his vehicle and drives off just in time.

Crazy Moments

7,224,616 次观看 • 8 个月前

$Fable 5 built this real-time ocean scene directly in the browser using Three.js, WebGPU and TSL, with no engine and no baked assets. The interesting part is not just that the water looks good. The whole system is being simulated: wave spectrum, GPU FFT, foam generation and refracted-ray caustics, all running live. This is exactly where frontier models start becoming genuinely useful for technical graphics work. Not by replacing years of rendering research, but by compressing the path from complex math to a working interactive result. A small, focused scene, but technically very serious. Cc: Adem Vessell$

Fable 5 built this real-time ocean scene directly in the browser using Three.js, WebGPU and TSL, with no engine and no baked assets. The interesting part is not just that the water looks good. The whole system is being simulated: wave spectrum, GPU FFT, foam generation and refracted-ray caustics, all running live. This is exactly where frontier models start becoming genuinely useful for technical graphics work. Not by replacing years of rendering research, but by compressing the path from complex math to a working interactive result. A small, focused scene, but technically very serious. Cc: Adem Vessell

Token Gremlin

21,731 次观看 • 3 个月前

every skeleton screen you've ever hand-coded is a waste of time you're literally measuring padding and guessing widths to build a worse version of a layout that already exists in your DOM so I made a package that just reads the real one

every skeleton screen you've ever hand-coded is a waste of time you're literally measuring padding and guessing widths to build a worse version of a layout that already exists in your DOM so I made a package that just reads the real one

goodfuture

775,819 次观看 • 6 个月前

Cleanliness on camera, but waste allegedly dumped into the Ganga River This is not awareness it’s hypocrisy. The Ganga is not just a river, it’s faith for millions. Real change needs responsibility and action, not just content for the camera.

Cleanliness on camera, but waste allegedly dumped into the Ganga River This is not awareness it’s hypocrisy. The Ganga is not just a river, it’s faith for millions. Real change needs responsibility and action, not just content for the camera.

Rakesh Kalotra

29,287 次观看 • 5 个月前

🚨 do you understand what just happened? Iran just turned the Strait of Hormuz into a toll road.. $1 per barrel.. paid in crypto or Chinese yuan.. not US dollars.. 20 million barrels pass through that strait every day.. that's 20% of the world's oil supply.. which means Iran just created a $20 million-a-day revenue stream out of a waterway it doesn't own.. using a war it didn't start as leverage.. and the payment has to be in crypto or yuan.. not dollars.. that's not just a toll.. that's Iran building a financial system that routes around American sanctions in real time.. the US spent decades making sure the world's oil runs on dollars.. Iran just made the world's most important oil chokepoint run on crypto and Chinese yuan.. and there's nothing Washington can do about it because they need that strait open more than anyone

🚨 do you understand what just happened? Iran just turned the Strait of Hormuz into a toll road.. $1 per barrel.. paid in crypto or Chinese yuan.. not US dollars.. 20 million barrels pass through that strait every day.. that's 20% of the world's oil supply.. which means Iran just created a $20 million-a-day revenue stream out of a waterway it doesn't own.. using a war it didn't start as leverage.. and the payment has to be in crypto or yuan.. not dollars.. that's not just a toll.. that's Iran building a financial system that routes around American sanctions in real time.. the US spent decades making sure the world's oil runs on dollars.. Iran just made the world's most important oil chokepoint run on crypto and Chinese yuan.. and there's nothing Washington can do about it because they need that strait open more than anyone

Tuki

3,632,416 次观看 • 6 个月前

GEMMA 4 26B ON AN RTX 4060 WITH A 248K TOKEN CONTEXT WINDOW 20 tokens per second and a context window so large you can feed it entire codebases, books and research papers in a single prompt this is not a cloud api and not a server rack, this is a regular consumer gpu running locally with llama.cpp and q4_k_xl quantization 248k context on an 8gb vram card was not supposed to be possible and here it is just running on someone’s desk the article below covers exactly which tools and configs make this kind of setup work in 2026 ↓

GEMMA 4 26B ON AN RTX 4060 WITH A 248K TOKEN CONTEXT WINDOW 20 tokens per second and a context window so large you can feed it entire codebases, books and research papers in a single prompt this is not a cloud api and not a server rack, this is a regular consumer gpu running locally with llama.cpp and q4_k_xl quantization 248k context on an 8gb vram card was not supposed to be possible and here it is just running on someone’s desk the article below covers exactly which tools and configs make this kind of setup work in 2026 ↓

leopardracer

56,865 次观看 • 4 个月前

Elon Musk gave the entire entertainment industry its expiration date, and he is the one building the thing that kills it. Musk: “My guess is that we see the first compelling half hour, pure AI show next year.” Next year. A complete show generated entirely by AI. No writers. No actors. No cameras. No sets. No crew. No studio. Just a prompt and enough compute to render a reality that never physically existed. And shows are the easy part. Musk: “I say probably we’re maybe three years away from AI does the whole video game.” A show plays the same way every time. A game has to generate a living world that reacts to every decision in real time across every single frame. That is a fundamentally harder class of problem. And Musk put three years on it. Right now a single AAA title takes seven years and half a billion dollars across thousands of engineers and artists just to ship it. Musk is describing a world where one person types a paragraph and gets something comparable. The entire value proposition of a multi-billion dollar industry lives inside that gap. And it closes in thirty-six months. But the prediction is not the story. The person making it is. This is not an analyst speculating from the sidelines. This is the man building the largest AI compute clusters on the planet. The man who built xAI from zero in under two years. The man stacking hundreds of thousands of GPUs into facilities designed to do exactly what he is describing. When Musk says three years, he is not guessing about what someone else might eventually ship. He is reading you a delivery date off his own roadmap. Every media company on Earth is valued on a single assumption. That quality content is expensive and difficult to produce at scale. That one assumption is the structural foundation underneath every studio, every network, and every publisher in existence. Musk is dismantling it with raw compute. The studios still parading thousand-person production teams are not demonstrating strength. They are advertising the exact cost structure that one person with a prompt and a GPU allocation is about to make irrelevant. And it does not stop at entertainment. If AI can generate an interactive world that responds to human input in real time, it can generate anything. Advertising. Architecture. Training simulations. Product design. Every industry built on humans manually constructing visual experiences frame by frame is sitting on the same countdown Musk just read out loud. Now zoom out. Because this is not just an industry story. For the entire history of human civilization, the distance between imagining a world and actually creating one required thousands of people, millions of hours, and billions of dollars. That distance built Hollywood. That distance built the gaming industry. That distance made content scarce and studios powerful. Musk is collapsing that distance to zero. When the gap between imagining something and it existing disappears, every business model built on the difficulty of creation disappears with it. That is not disruption. That is a full inversion of how human beings create. Musk did not make a casual prediction on that podcast. He told you what he is building. He told you the timeline. And he told you which industries do not survive it. The entertainment industry is still debating whether this future is real. Musk is not part of that debate. He is building. And he just told you the delivery date.

Elon Musk gave the entire entertainment industry its expiration date, and he is the one building the thing that kills it. Musk: “My guess is that we see the first compelling half hour, pure AI show next year.” Next year. A complete show generated entirely by AI. No writers. No actors. No cameras. No sets. No crew. No studio. Just a prompt and enough compute to render a reality that never physically existed. And shows are the easy part. Musk: “I say probably we’re maybe three years away from AI does the whole video game.” A show plays the same way every time. A game has to generate a living world that reacts to every decision in real time across every single frame. That is a fundamentally harder class of problem. And Musk put three years on it. Right now a single AAA title takes seven years and half a billion dollars across thousands of engineers and artists just to ship it. Musk is describing a world where one person types a paragraph and gets something comparable. The entire value proposition of a multi-billion dollar industry lives inside that gap. And it closes in thirty-six months. But the prediction is not the story. The person making it is. This is not an analyst speculating from the sidelines. This is the man building the largest AI compute clusters on the planet. The man who built xAI from zero in under two years. The man stacking hundreds of thousands of GPUs into facilities designed to do exactly what he is describing. When Musk says three years, he is not guessing about what someone else might eventually ship. He is reading you a delivery date off his own roadmap. Every media company on Earth is valued on a single assumption. That quality content is expensive and difficult to produce at scale. That one assumption is the structural foundation underneath every studio, every network, and every publisher in existence. Musk is dismantling it with raw compute. The studios still parading thousand-person production teams are not demonstrating strength. They are advertising the exact cost structure that one person with a prompt and a GPU allocation is about to make irrelevant. And it does not stop at entertainment. If AI can generate an interactive world that responds to human input in real time, it can generate anything. Advertising. Architecture. Training simulations. Product design. Every industry built on humans manually constructing visual experiences frame by frame is sitting on the same countdown Musk just read out loud. Now zoom out. Because this is not just an industry story. For the entire history of human civilization, the distance between imagining a world and actually creating one required thousands of people, millions of hours, and billions of dollars. That distance built Hollywood. That distance built the gaming industry. That distance made content scarce and studios powerful. Musk is collapsing that distance to zero. When the gap between imagining something and it existing disappears, every business model built on the difficulty of creation disappears with it. That is not disruption. That is a full inversion of how human beings create. Musk did not make a casual prediction on that podcast. He told you what he is building. He told you the timeline. And he told you which industries do not survive it. The entertainment industry is still debating whether this future is real. Musk is not part of that debate. He is building. And he just told you the delivery date.

Dustin

22,522 次观看 • 2 个月前

I FOUND A COUPLE FORMAT THAT GETS 7M+ VIEWS WITH ONE HAND AND ONE PAIR OF GLASSES. 12 SECONDS. NO KISS. NO CAPTION. JUST A CAMERA ANGLE THAT MAKES YOUR BRAIN LIE TO ITSELF. Thread. First frame. Girl in black, camera below her chin. A man's hand enters from above and grabs her hair. Pulls. You already know what you think is about to happen and that's why you're still here. 0:01. Hand grips the hair, pulls her head back. Angle is from below looking up. This is the exact POV of every clip on sites you don't talk about. The framing is doing all the work and the video hasn't even started. 0:03. She's wearing glasses. His hand comes down and takes them off. That's it. He removed her glasses. But the way the hand moves from her hair to her face, the way she looks up with her lips parted, none of it reads as "taking off glasses." It reads as what you decided in the first second. 0:07. Hand grabs her chin, tilts her face up. She's looking into the camera from below with his fingers under her jaw. On paper a guy is holding his girlfriend's face. On paper it's nothing. On screen it's everything. The video loops and you're watching the hair grab again, already knowing it's just glasses, and it looks exactly the same. Knowing the punchline doesn't undo the setup. Your brain sees it the same way every time. The format: hand from above, camera from below, one accessory. Glasses, hair tie, necklace, doesn't matter. That geometry is the entire trick. Black top, pearl necklace, white room. If she was in sweats on a couch this would be a vlog. In this outfit with this lighting it's a scene. If you see a hand from above and a camera from below, your brain already finished the video for them. She didn't do anything. He just took off her glasses.

I FOUND A COUPLE FORMAT THAT GETS 7M+ VIEWS WITH ONE HAND AND ONE PAIR OF GLASSES. 12 SECONDS. NO KISS. NO CAPTION. JUST A CAMERA ANGLE THAT MAKES YOUR BRAIN LIE TO ITSELF. Thread. First frame. Girl in black, camera below her chin. A man's hand enters from above and grabs her hair. Pulls. You already know what you think is about to happen and that's why you're still here. 0:01. Hand grips the hair, pulls her head back. Angle is from below looking up. This is the exact POV of every clip on sites you don't talk about. The framing is doing all the work and the video hasn't even started. 0:03. She's wearing glasses. His hand comes down and takes them off. That's it. He removed her glasses. But the way the hand moves from her hair to her face, the way she looks up with her lips parted, none of it reads as "taking off glasses." It reads as what you decided in the first second. 0:07. Hand grabs her chin, tilts her face up. She's looking into the camera from below with his fingers under her jaw. On paper a guy is holding his girlfriend's face. On paper it's nothing. On screen it's everything. The video loops and you're watching the hair grab again, already knowing it's just glasses, and it looks exactly the same. Knowing the punchline doesn't undo the setup. Your brain sees it the same way every time. The format: hand from above, camera from below, one accessory. Glasses, hair tie, necklace, doesn't matter. That geometry is the entire trick. Black top, pearl necklace, white room. If she was in sweats on a couch this would be a vlog. In this outfit with this lighting it's a scene. If you see a hand from above and a camera from below, your brain already finished the video for them. She didn't do anything. He just took off her glasses.

framexin

63,594 次观看 • 2 个月前

What the fuck is China building? This is not a clip from movie, this is a real project in China. Due to the trade war, there’s a video of a Chinese guy said, “we both benefit from trade, U.S. and China. But only one of us is using the wealth to build for our people”. that is 🇨🇳

What the fuck is China building? This is not a clip from movie, this is a real project in China. Due to the trade war, there’s a video of a Chinese guy said, “we both benefit from trade, U.S. and China. But only one of us is using the wealth to build for our people”. that is 🇨🇳

chásè yú 👁‍🗨

2,764,373 次观看 • 1 年前

Bob from Twin Peaks was just a guy that worked in the background of the show as set dresser. Then David Lynch noticed his image, including a reflection in a mirror, and liked the eerie presence. That led Lynch to put Silva on camera in that scene.

Bob from Twin Peaks was just a guy that worked in the background of the show as set dresser. Then David Lynch noticed his image, including a reflection in a mirror, and liked the eerie presence. That led Lynch to put Silva on camera in that scene.

Emir Han

165,145 次观看 • 6 个月前

The future of agriculture lies in optimization. A system like this costs very little: a drone with a camera and a computer vision system accurate enough to count and identify plants or diseases. It's so easy that anyone can make it at home for their own crops.

The future of agriculture lies in optimization. A system like this costs very little: a drone with a camera and a computer vision system accurate enough to count and identify plants or diseases. It's so easy that anyone can make it at home for their own crops.

Marco Franzon

120,683 次观看 • 4 个月前

Single video → a reframeable 4D Gaussian Splatting scene. Not a sequence of separately built 3D frames played back like a video. This is one continuous space-time scene, reconstructed from a single clip shot on an iPhone 16. We combine feed-forward Gaussian generation, 3D tracking, and 4D Gaussian Splatting, aiming to deliver it as a compact 4D video file that runs on your phone. Still early R&D. The goal: make 4DGS something anyone can create and experience, not just researchers with a camera rig.

Single video → a reframeable 4D Gaussian Splatting scene. Not a sequence of separately built 3D frames played back like a video. This is one continuous space-time scene, reconstructed from a single clip shot on an iPhone 16. We combine feed-forward Gaussian generation, 3D tracking, and 4D Gaussian Splatting, aiming to deliver it as a compact 4D video file that runs on your phone. Still early R&D. The goal: make 4DGS something anyone can create and experience, not just researchers with a camera rig.

KIRI Engine - 3D Scanner App

31,871 次观看 • 2 个月前