InSpatio｜影溯

We build 3D world models toward spatial intelligence 🌐
Enabling AI to understand, simulate, and interact with the 3D physical world.

[InSpatio｜影溯 @InSpatio_AI]

A photo shouldn’t have to stay a photo.
A video shouldn’t have to stay a video.
They can become worlds.

🌍 InSpatio-World 1.5 is here.
Our real-time 4D world model now supports:
🖼️ Single-image input
🖼️🖼️ Multi-image input
🌐 Panorama input
🎬 Video input

From visual input to a dynamic, navigable 4D world — explore beyond the original viewpoint and move through the scene in space and time.
Open-source.Real-time. Ready to explore.

Live Demo:
🔗 https://t.co/Fn9OTgg4eG
Code:
🔗 GitHub - inspatio/inspatio-world-v1.5
Weights:
🔗 https://t.co/3ujZ4Z66na
Project Page:
🔗 https://t.co/ZvgeTmZEnP

[InSpatio｜影溯 @InSpatio_AI]

Expolre More：
🌐 Live Demo
https://t.co/Fn9OTgg4eG
💻 Code
https://t.co/IyFz49KMKz
🤗 Weights
https://t.co/3ujZ4Z66na
🔗 Project Page
https://t.co/ZvgeTmZEnP

[InSpatio｜影溯 @InSpatio_AI]

A photo shouldn’t have to stay a photo.
A video shouldn’t have to stay a video.
They can become worlds.

🌍 InSpatio-World 1.5 is here.
Our real-time 4D world model now supports:
🖼️ Single-image input
🖼️🖼️ Multi-image input
🌐 Panorama input
🎬 Video input

From visual input to a dynamic, navigable 4D world — explore beyond the original viewpoint and move through the scene in space and time.
Open-source.Real-time. Ready to explore.

Live Demo:
🔗 https://t.co/Fn9OTgg4eG
Code:
🔗 GitHub - inspatio/inspatio-world-v1.5
Weights:
🔗 https://t.co/3ujZ4Z66na
Project Page:
🔗 https://t.co/ZvgeTmZEnP

[InSpatio｜影溯 @InSpatio_AI]

Expolre More：
🌐 Live Demo
https://t.co/Fn9OTgfwp8
💻 Code
https://t.co/IyFz49KeV1
🤗 Weights
https://t.co/3ujZ4Z5yxC
🔗 Project Page
https://t.co/ZvgeTmZ6yh

[InSpatio｜影溯 @InSpatio_AI]

A photo shouldn’t have to stay a photo.
A video shouldn’t have to stay a video.
They can become worlds.

🌍 InSpatio-World 1.5 is here.
Our real-time 4D world model now supports:
🖼️ Single-image input
🖼️🖼️ Multi-image input
🌐 Panorama input
🎬 Video input

From visual input to a dynamic, navigable 4D world — explore beyond the original viewpoint and move through the scene in space and time.
Open-source.Real-time. Ready to explore.

Live Demo:
🔗 https://t.co/Fn9OTgg4eG
Code:
🔗 GitHub - inspatio/inspatio-world-v1.5
Weights:
🔗 https://t.co/3ujZ4Z66na
Project Page:
🔗 https://t.co/ZvgeTmZEnP

[InSpatio｜影溯 @InSpatio_AI]

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 ↓

[ModelScope @ModelScope2022]

@InSpatio_AI releases InSpatio-World 1.5, turning images and videos into real-time, explorable 4D worlds.
🤖 https://t.co/o42sQcECQD
📄 https://t.co/12tiNfFKAx

🏆 The 1.3B model scores 68.72 on WorldScore-Dynamic, ranking #1 among evaluated real-time and interactive methods while reaching up to 24 FPS.
🌐 A single image, four images, a panorama, or a video can become a navigable scene with wide viewpoint changes and target camera trajectories.
🎥 Next-view prediction preserves motion, spatial structure, and visual style across space and time, with support for bullet-time creation.
📐 For video inputs, Depth Anything 3 automatically estimates missing depth and per-frame camera intrinsics and extrinsics.
🧠 Spatiotemporal autoregression maintains a persistent world state for consistent long-horizon exploration.
📜 Code: Apache 2.0. Dependencies retain their own licenses.

[InSpatio｜影溯 @InSpatio_AI]

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! 😆
🔗 https://t.co/VaguGSnRqZ
Try it on the Web: 🔗 https://t.co/3ZrCuGZCKS
Paper:
🔗 https://t.co/gMHB9b5vjR
Code & weights:
🔗 https://t.co/ofbNZMjtcF
Project page:
🔗 https://t.co/GRkQm4oTIh

#AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

[InSpatio｜影溯 @InSpatio_AI]

@369Inspire we will open source it, we’re preparing more technical details and results; stay tuned!

[InSpatio｜影溯 @InSpatio_AI]

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

[InSpatio｜影溯 @InSpatio_AI]

@virtualfilmer 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 :)

[InSpatio｜影溯 @InSpatio_AI]

@damimorley1 Love to hear that:) would be great to compare notes. Monocular 4D reconstruction in the wild still has so many interesting challenges😆

[InSpatio｜影溯 @InSpatio_AI]

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

[Junhan Sun @DavidSunok47]

LeWM predicts action effects, but searches 9,000 sequences to act.

Introducing INTACT: an end-to-end unified JEPA that completes the other half of LeWM: intent to action.

Only 1 epoch. 0 search.
95.33% Direct macro SR.
2.9-5.5 ms inference.
~300× lower planning latency.

[InSpatio｜影溯 @InSpatio_AI]

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! 💪

[Junhan Sun @DavidSunok47]

LeWM predicts action effects, but searches 9,000 sequences to act.

Introducing INTACT: an end-to-end unified JEPA that completes the other half of LeWM: intent to action.

Only 1 epoch. 0 search.
95.33% Direct macro SR.
2.9-5.5 ms inference.
~300× lower planning latency.

[InSpatio｜影溯 @InSpatio_AI]

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

[InSpatio｜影溯 @InSpatio_AI]

📸 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

[InSpatio｜影溯 @InSpatio_AI]

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. 👀

[InSpatio｜影溯 @InSpatio_AI]

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.

[InSpatio｜影溯 @InSpatio_AI]

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 🧪👀