Expolre More： 🌐 Live Demo world.inspatio.com/ 💻 Code github.com/inspatio/inspatio… 🤗 Weights huggingface.co/inspatio/worl… 🔗 Project Page inspatio.github.io/inspatio-…

Expolre More： 🌐 Live Demo world.inspatio.com/ 💻 Code github.com/inspatio/inspatio… 🤗 Weights huggingface.co/inspatio/worl… 🔗 Project Page inspatio.github.io/inspatio-…

Thanks @ModelScope2022 for the feature 🙌 InSpatio-World 1.5 is now available on ModelScope. From images and videos to real-time, explorable 4D worlds — we’re excited to bring our latest world model to more developers and researchers. Explore it now ↓

2D is what the camera sees.👀 3D is what the world is. 🌍 Today, we’re proudly open-sourcing QuerySplat — an open-source feed-forward 3D model that turns a few unposed images into a navigable 3D scene in seconds (run on 4090🪶). Your input: a few unposed images Our output: a sharp, navigable 3D scene — generated in seconds! 🚀 🧠 organize scenes with 3D queries, not pixel-bound Gaussians 📷 no camera poses or manual calibration required ⚡ reconstruct new scenes in a single forward pass ✨ preserve sharp geometry and high-frequency appearance 🏆 achieve state-of-the-art results on DL3DV-Evaluation 🔓 code and model weights are now open-source From pixels to scenes, we are making 3D generation scalable. Try our free iOS app — it’s a lot of fun! 😆 🔗 apps.apple.com/us/app/crysta… Try it on the Web: 🔗 topos-lite.inspatio.com/ Paper: 🔗 arxiv.org/abs/2608.01186 Code & weights: 🔗 github.com/inspatio/queryspl… Project page: 🔗 inspatio.github.io/queryspla… #AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

we will open source it, we’re preparing more technical details and results; stay tuned!

Great question. multi-person interactions, occlusion, facial detail, and lip synchronization are among the hardest cases. We’re actively testing these scenarios and will share more results as the system improves :)

Love to hear that:) would be great to compare notes. Monocular 4D reconstruction in the wild still has so many interesting challenges😆

Excited to introduce INTACT — our latest collaboration with Zhejiang University, Tsinghua University, and RobertParty. While LeWM excels at predicting what happens next (action effects), it still relies on searching through up to 9,000 future sequences just to decide what to do now. We asked: Why search when you can reason? INTACT is the missing half of LeWM — an end-to-end unified JEPA that directly bridges intent → action, no search required. 📊 Key results: ✅ Only 1 epoch to train 🔍 0 search during inference 🎯 95.33% Direct macro Success Rate ⚡ 2.9 – 5.5 ms inference time 🚀 ~300× lower planning latency than LeWM No tree. No rollouts. Just pure, fast, zero-search intention grounding. #wroldmodel #JEPA #AI #leWM

From world models🌍 to world action. 🤖 INTACT closes the loop from latent intent to real-time control — end-to-end, search-free, and millisecond-fast. Proud to be part of this work! 💪

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

And yes! Topos-Lite will be open-sourced🌍! Can’t wait to see what the community builds with it. 😎 #opensource

What excites us most is the idea that important moments might no longer have to live only as photos or videos. They could become 3D memories you can actually look around. ✨ For the first time, that starts to feel genuinely practical: fast, affordable, and surprisingly easy to create. While testing Topos-Lite, we got to “visit” a remote teammate’s living room and meet their pet, all reconstructed in 3D from just a few images. Being able to drag the scene, rotate the camera, and explore it from different angles was honestly a little surreal. And very fun. 🐾 It felt less like looking at a photo and more like pausing a moment in time, preserving a small piece of the real world that you can come back to later. We’re actively working to bring experiences like this into real products. If this gives you an idea for memories, social apps, games, spatial computing, or something completely unexpected, we’d love to hear it. Our DMs are open. 👀

📸 A few photos. ⚡ A few seconds. A high-quality 3D scene！🎬 Meet Topos-Lite, our new 3D Gaussian Splatting model. With just a few sparse multi-view images, it can generate a high-quality, renderable 3D scene in few seconds We’re excited to share more soon. The technical report is coming shortly — stay tuned and stay in touch. 👀 #ToposLite #3DGS #3DGeneration #SpatialAI #AIGC #photograph #3DArtwork

Turn any video or idea into an editable 3D world. SpatioSim turns real-world captures and concepts into navigable scenes you can edit, explore, and simulate inside. Built for creators, game teams, and robotics labs. 🎬🎮🤖 Demo access soon.

Introducing SpatioSim. From ideas and real-world captures to editable 3D Worlds. Generate. Edit. Simulate. Built for creators🎬, game makers🎮, and robotics teams🤖. Beta soon 🧪👀

The current release of InSpatio‑World is an unoptimized version. The fully optimized version, consistent with our online live demo and reaching ~24 FPS on a datacenter GPU and 10 FPS on an RTX 4090, will be released together with our technical report within 2 weeks. Stay tuned!🪄

This is awesome — thanks for diving in so fast 🙌 Great to see people already experimenting with different pipelines 😉🌐

Thanks for the love! We’re already seeing developers start building their own projects with it, so feel free to jump in 🙌 We’ll also be releasing a tech report soon. 🔜🌐

Will share a full technical write-up very soon. Stay tuned! 👀🌐

Runs smoothly on a single 4090 in our tests 👍