Right now, 4D capture mostly belongs to labs, studios,... and expensive multi-camera rigs. Our goal at KIRI has always been different: put spatial capture in the hands of regular people, on the device they already carry with them. This is a work in progress, but it’s a huge step toward consumer level 4D scanning: record a normal video once, then reframe that moving moment afterward 🤩show more

This is some quietly impressive work on making video... world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.show more

Kling 2.6 Motion Capture is so good. It's a... huge leap forward. We've been able to do motion capture with AI for a while, but the quality bump finally made this approach useful. Here are the steps: - Get a reference video - record it or get a stock video - Grab the start frame of that video - Edit it using Nano Banana Pro. Ask to replace character and background. - Select the Kling 2.6 Motion Capture model in the video generator on Freepik (now Magnific) - Upload reference video + set the edited start frame - Video prompt can be simple e.g. "Gandalf dancing"show more

Yeaah with Kartel.ai and Jesse Wellens ! So training... Lora for character on Flux and also for Wan 2.1 14B ( using dataset video ) make a Huge difference. So here you are seeing a volumetric capture of Jesse Wellens that we did in at the spatial studio of Kartel.ai We use a a World Labs gaussian splatting to create a simple environment that we put with the volumetric capture in our own webgl viewer ( out soon for everyone ). After that, We use after this output in a ComfyUI workflow with Wan Fun control ( a bit similar Vace but its working for Wan 14B) with the double loras , the first to generate the first frame with flux, and the second one to guide the generation of Wan 2.1 Control. So we keep very good consistency of character and position, and creating amazing worlds :) ! Hope you will find it cool !show more

So many wins to celebrate today! Jarren and Kolette... having a show together in Gensan is already a huge win. Seeing them happy and carefree together? Another win. But the ultimate highlight has to be them performing the Jarlette dance, it’s the best win of all! Let’s not forget, the Jarlette dance was Moonstrings’ special gift to them. It’s the dance step they created together, which blew up on TikTok thanks to Moonstrings’ efforts. We’ve been waiting months to see them perform this, and today, we finally got to witness them perform it on stage, right in front of so many Moonstrings. Today truly belongs to Jarlette and Moonstrings, a celebration of hard work, love, and shared joy. What an unforgettable day! KOLETTE MEMErriest XMAS JARLETTE GENSHINES TOGETHERshow more

Sneak peek from the lab. Work in progress of... the real-time face tracking, via iPhone, Clone v2 cinematic rig. Simple viewport capture, no lighting or shading. Effective expression capture is key for conveying emotions accurately with your Clones. Our new cinematic rig has been constructed with flexibility in mind. We've carefully refined the 52 blend shapes that drive the facial expressions, and the face controls themselves, to achieve a more natural look. We have more iteration cycles to go through before we hit our target but you can already see a great difference from v1. This upgrade opens up a world of possibilities, from high-fidelity dynamic VRMs adaptable to various platforms to virtual production capabilities and V-Tubing with improved face filters. Our goal is simple: To help eliminate technical barriers and provide a more seamless and inclusive utility for all of our community, all while ensuring quality remains at the core of everything we do.show more

❤️ Lewis Hamilton: “I started this voyage, dream of... moving to Ferrari and being on the top step with them and this podium, it’s taken a long time…” “Longer than I had hoped and after a difficult last year, to be able to be part of developing with them, working with them over the past year gives me huge pride and such privilege to be part of this brand and they provided us with a very solid car, we got a great package, particularly through corners, we just gotta step it up to be able to keep up with them on the straights.” “But yeah… It’s a very special day, especially ‘cause it’s mother’s day, my mum is here… just yeah, it’s been an awesome week.”show more

Interesting development - I was told numerous stories about... what happened yesterday at Crosby. One being it was a group of Asian men attacking teenage girls. Some as young as 14. I dismissed it as rumours and told people to watch out for racism. People unfairly targeting Asians and making lies up about them. But I’ve just been sent this. Now unless there is a conspiracy to frame them. It’s now looking like this is the case. The only other possibility is that this was 2 separate incidents. But either way we can’t live in peace with savages who do this on a public beach in front of families. I don’t want to speculate. So I’m going to bite my tongue on this for the time being in case I’m wrong. It has since been confirmed that teenage girls have been attacked with a bladed item. But the attacker has not been confirmed. I’m currently speaking to the Echo to work out what’s going on.show more

A driver caught on surveillance camera flying through an... intersection in Murray Utah and the internet is going crazy trying to figure out who is at fault here - this is exactly the kind of reckless driving that turns a normal afternoon into a tragedy in a split second. Intersections are already one of the most dangerous spots on any road and when somebody decides the rules don’t apply to them everybody around them becomes a victim of that decision. Watch the video and drop your verdict in the comments.show more

On the paper, there's a clear count of how... many times fans tilted their heads toward Ling (L), toward Orm (O), or toward both (LO) while taking photos during the first FMT in Bangkok. And when you look at Orm’s numbers, it's painfully low 🙂 First of all, I completely disagree with and feel very disgusted by this kind of behavior. What pisses me off even more is the double standard. Why is it that when Orm is the one being hurt, people tend to stay silent, as if it’s normal? Yet when it happens to someone else, suddenly the outrage is everywhere. Why is that? Because Orm is humble? Because she always smiles and pretends to be okay, so people think it’s fine to overlook her pain? Orm has been enduring this kind of treatment since the very beginning. It’s not something recent. It’s not something that happened once. It’s been happening again and again, and it’s still happening now. None of Orm’s fans are okay with this, I am not okay with this too, honestly sick of it. But I’ve accepted that, with a fandom this big, we can’t control everything. Still, there are many people who respect both of them, and that gives me a bit of peace But let’s be clear, accepting pain doesn’t mean it’s justified. So to those out there playing the “victim card” while turning a blind eye to everything Orm has been through.... You want to talk about fairness? Then let’s talk about Orm first 🙂show more

In the summer of 2023, I cold emailed Jensen... Huang and asked to capture a NeRF of him at SIGGRAPH. He responded in about an hour and said yes. A radiance field is, in the simplest terms, akin to a 3D photograph. A moment in time, so completely reconstructed that you can move through it and see it from angles the original cameras never occupied. NeRFs were the original method. Gaussian splatting, which debuted at that same SIGGRAPH, has since become the dominant form of radiance field. I called my late friend James, who told me we needed to begin practicing immediately. We ran capture after capture for weeks until we consistently got the capture time down to ~30 seconds with one camera. Later, in a hallway at the LA Convention Center during SIGGRAPH, I captured the portrait you're seeing now, a full 360° gaussian splat of Jensen, rendered here as a 2D flythrough. Afterward, I continued the conversation with him and members of his team to make the case for radiance fields as a foundational representation for imaging. To my surprise, they listened. Three years later, NVIDIA has several works, including NuRec, fVDB, 3DGRUT, and gsplat all utilizing radiance fields. The landscape has evolved enough that the reasoning is obvious. Gaussian splatting has begun to ship across some of the world’s largest industries, including autonomous vehicles, AEC, geospatial, media and entertainment, robotics, e-commerce, hospitality. It’s become clear that lifelike 3D is here to stay. And yet I think we will look back and be disappointed by how late we started taking 3D portraits of the people around us, just like how we have sparse 2D photos of our grandparents and great grandparents. We have billions of photographs of the people we know and love, but almost no radiance fields of them. I'll be returning to SIGGRAPH in LA where this was initially captured three years ago, with the landscape looking significantly different. Radiance fields are more under deployed than ever relative to what they can do. I'm excited for the future of imaging, and for 2D to transition into 3D. I have a few things up my sleeve that I think will make that case plainly.show more

The situation in the Middle East right now is... serious, and many people in the region are going through uncertain times. Dubai and the entire Gulf region have always been incredibly important for our films and for our boss. Millions of Indians live and work there, and a massive fan base of Rocking Star stands proudly in that region. For a film of this scale, the experience is meant to be shared together by fans across the world at the same time. When such a large section of our audience is facing tension and uncertainty, it only makes sense to wait for the right moment so everyone can celebrate the film together in theatres. This decision shows responsibility and respect for fans everywhere. Cinema is about bringing people together, and the goal is for every fan, whether in India, Dubai, or anywhere in the world, to enjoy the experience without worry. Real fans understand this. The celebration will be bigger when the time is right. 🔥show more

One of the followers sent this video in of... him giving it to the Commi’s in Bootle. There is a known theory that the reason we have all this is because of Russia/Qatar/Iran are spending billions on bot accounts pushing all this on the internet. They also fund activists to push this on our streets and university campuses. Knowing the divide and damage it causes to society. They also push Palestine protests which is why everyone is up in arms about Palestine but no other genocides happening right now. Not a peep out of them. The people who stand at hotels with refugees welcome signs. Most of them are paid to do so. They are literally carrying out the dirty work for countries that want to bring us down. And they have the cheek to call normal everyday people who just want to live in peace the “divisive” ones. We will never live in a peaceful society while these people exist. Even if we do free Palestine. They will just move onto something else to divide our society. For them the revolution never ends.show more

Our community in Austin once again proved that distance... means nothing when hearts are close. They put together a large shipment of winter clothing and gear for the defenders- from fleeces and jackets to all the essentials. Everything was washed, neatly packed, and prepared with so much care. A lot of hard work, a lot of love, and true team spirit. Huge thanks to Nataliya Kovalchuk for the organization, endurance, and those very real “spa days” for the clothes - washing all of this was a quest of its own. Special thanks to david D. for the donations - thanks to you, this support was possible. Everything has already arrived in Kyiv and Kharkiv and has been distributed to different brigades. Photo reports coming soon. And a small bonus - this time I didn’t have to carry everything myself 😄 Thank you to everyone who helped. Our community is always there, even from far away 💙show more

Trained on zero real-world data. Learned to walk, pick... up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:show more

🚨 Quantum computers don’t run on electricity. They run... on light. And that’s been the problem. Each quantum system needs very specific laser colors to control atoms and qubits. Until now… those lasers were: huge expensive stuck in labs But scientists just changed that. They built a chip that can generate ANY wavelength of light inside a tiny circuit. ~10,000 photonic circuits full spectrum control on a single chip This is massive. Because it means: Quantum computers could go from room-sized labs… to portable systems. So the real question is If we can control reality at the quantum level with light… what happens when that control fits in your hand? Follow me the future won’t be powered by electrons.show more

If you watch the latest Optimus dancing video in... slow motion, you’ll notice that it’s not just dancing, but it’s hopping and balancing on one foot. Also, the string in the back isn’t even holding Tesla Bot up! This level of dynamic balance and control is EXTREMELY difficult to achieve for a humanoid robot. What Tesla is doing right now with Optimus is years ahead of what people realize.show more

Wonderland: Navigating 3D Scenes from a Single Image Contributions:... • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.show more