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 single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR... show more

Hao Zhao

1,429 subscribers

52,340 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

27 条评论

the.PM 的头像

the.PM1 个月前

In a year or so this will be the standard way to generate AI videos and all the investments into AI video companies will go to near zero haha

0xinha 的头像

0xinha1 个月前

Awesome! Can i use it in UEFN? @HaoZhao_AIRSUN

Peachy J 的头像

Peachy J1 个月前

Going from one image to a full UE5 world is impressive.

Vital 👁️ 的头像

Vital 👁️1 个月前

When are you guys planning on releasing? This is awesome!

UnrealPixelation 的头像

UnrealPixelation1 个月前

Ok, I'm intrigued. Let's see how this will hold up for real

artofelection 的头像

artofelection1 个月前

Impressive. Human face and body next?

Chris Rupp 的头像

Chris Rupp1 个月前

I've been working on this exact sort of thing...it's inspiring, validating, and scary at the same time to see you all making such excellent progress. Congrats! Will be following.

Shi Yorkchen 的头像

Shi Yorkchen1 个月前

Great, when can we get Lumera-2K?

Selorm Xatse 的头像

Selorm Xatse1 个月前

Interesting how far and fast the technology is advancing in facilitating storytelling.

Storm 的头像

Storm1 个月前

Groundbreaking! The future of Level Design!!

Chamu 的头像

Chamu1 个月前

@CSProfKGD Just do it for UE metahuman!

BitePDF 的头像

BitePDF1 个月前

Wow how about making product trailers.

马睿的头像

马睿1 个月前

👏

Shahar Nechmad 的头像

Shahar Nechmad1 个月前

This is super cool! It's kind of crazy to see the advancements in world models and our ability to model real-life scenes. How much time does a generation take?

𖥧 sofi w. 的头像

𖥧 sofi w.1 个月前

Totally agree with this

Melison 的头像

Melison1 个月前

wow! Gorgeous. Is there any time for release?

Neo Vector 的头像

Neo Vector1 个月前

Single image to editable engine scene is wild. Still a pretty big gap between this and actually usable output though.

Singulith 的头像

Singulith1 个月前

素晴らしいプロジェクトです｡期待しています!😃

Internet Labs 的头像

Internet Labs1 个月前

Turning a single flat image into a fully interactive UE5 world with real layouts and lighting instead of just another Gaussian blob is the exact level-up 3D artists have been waiting for.

Irie Rubz 的头像

Irie Rubz1 个月前

madness wow

Soph v, 的头像

Soph v,1 个月前

This is so true

Azeem 的头像

Azeem1 个月前

the key technical innovation is generating engine-native assets meshes, layouts, and lighting, rather than visual approximations like point clouds or Gaussians. This makes the output immediately usable in production pipelines.

danci.exr 的头像

danci.exr1 个月前

Very impressive, will it also detect semi-transparent objects and apply to a proper shader?

X Æ A-12 的头像

X Æ A-121 个月前

witchcraft !

Hang Chu 的头像

Hang Chu1 个月前

this is magic! how much token $ does each scene take on average?

Hao Zhao 的头像

Hao Zhao1 个月前

about 100 rmb actually

blackbox 的头像

blackbox1 个月前

Object-level meshes is the claim I care about. In my Grok Imagine work wide interior shots collapse and only tight crops stay coherent, so a full-room reconstruction from one image is a big ask.

相关视频

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -

How about one image straight to an editable UE5 or Blender scene? Lumera just dropped paper - Engine-Native Editable 3D World Reconstruction with Objects & Lighting. You give it an image. It figures out what's in the scene, rebuilds every object as a separate mesh, then recreates the lighting as actual engine lights you can move and tweak. Even pulls an HDR environment out of the shot. The lighting part is the big deal here. Every other image-to-3D approach bakes it in. Lumera keeps it a parameter, like the scene was built in the engine from the start. Code and weights marked as "Soon". Paper -

Stefan 3D AI

47,223 次观看 • 1 个月前

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Tengfei Wang

552,975 次观看 • 6 个月前

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

Markandey Sharma

31,374 次观看 • 1 个月前

🚨 A SINGLE IMAGE can now become an entire 3D WORLD. I’m talking about Hyper3D WorldGen. It follows a structured method where EVERY OBJECT is an individual editable 3D asset. It also reconstructs: → Spatial positions & relationships → Object arrangements → Collisions → Mass → Friction etc... On the other hand, 3D Designers take much time to do the same things Free Trail Link Below👇

🚨 A SINGLE IMAGE can now become an entire 3D WORLD. I’m talking about Hyper3D WorldGen. It follows a structured method where EVERY OBJECT is an individual editable 3D asset. It also reconstructs: → Spatial positions & relationships → Object arrangements → Collisions → Mass → Friction etc... On the other hand, 3D Designers take much time to do the same things Free Trail Link Below👇

SARAH

87,362 次观看 • 1 个月前

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 次观看 • 2 年前

Generate an interactive 3D world ✨ I opened this project in Cursor and uploaded an image of a cozy bookstore. The agent then generated the environment, chose objects to turn into 3D meshes, added colliders, and created sound effects 🤯

Generate an interactive 3D world ✨ I opened this project in Cursor and uploaded an image of a cozy bookstore. The agent then generated the environment, chose objects to turn into 3D meshes, added colliders, and created sound effects 🤯

Justine Moore

77,616 次观看 • 5 个月前

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive 3D worlds from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

Tencent Hy

373,065 次观看 • 6 个月前

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 次观看 • 6 个月前

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.

Sharon Riley

21,697 次观看 • 1 个月前

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing WonderPlay: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

Hong-Xing (Koven) Yu

58,065 次观看 • 1 年前

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

Georgia Gkioxari

116,203 次观看 • 10 个月前

Image-Blaster is a Claude skill that can create an entire 3D environment from a single image. The special sauce here is that it also extracts key environment elements and converts them into their own separate 3D models. Full YT video:

Image-Blaster is a Claude skill that can create an entire 3D environment from a single image. The special sauce here is that it also extracts key environment elements and converts them into their own separate 3D models. Full YT video:

Matt Workman

25,206 次观看 • 5 个月前

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

Alvaro Cintas

56,246 次观看 • 4 个月前

What if we can simulate an *interactive 3D world*, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

What if we can simulate an interactive 3D world, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

Wenlong Huang

279,355 次观看 • 9 个月前

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Ihtesham Ali

45,956 次观看 • 5 个月前

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

SpAItial AI

10,765 次观看 • 5 个月前

From a single image to a full robotics simulation. 360 image → Marble → 3D environment → Robotics sim This is how we scale world creation for embodied AI with Lightwheel, turning lightweight capture into simulation-ready environments in minutes, not weeks.

From a single image to a full robotics simulation. 360 image → Marble → 3D environment → Robotics sim This is how we scale world creation for embodied AI with Lightwheel, turning lightweight capture into simulation-ready environments in minutes, not weeks.

World Labs

46,356 次观看 • 9 个月前