Загрузка видео...

Не удалось загрузить видео

На главную

⚡️Your video → a 3D scene. Just in seconds.⚡️ Only *one* model. No more steps❌. Just results🔝. #WorldMirror reconstructs everything (3DGS, depth, cameras) from any inputs (image, video, 3D prior) *all-at-once*! code: arxiv:

DylanTFWang's profile picture

Tengfei Wang

3,690 subscribers

67,403 просмотров • 11 месяцев назад •via X (Twitter)

#WorldMirror
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Kushal Mittal
Kushal Mittal11 месяцев назад

if I have a 3d scene on blender how can I make 3dgs out of that so people can walk through it on web? have been trying to find a solution to that but can’t seem to find anything.

Фото профиля Tristan
Tristan11 месяцев назад

Any news on improved reconstruction from a single image? Current implementation leaves too many holes (sparse Gaussians) for anything resembling professional applications of the output .ply

Фото профиля Peter MOUEZA🇲🇫
Peter MOUEZA🇲🇫11 месяцев назад

Note100 : 99.7

Фото профиля Bobcat
Bobcat11 месяцев назад

Exciting!

Фото профиля Thomas YL Lin
Thomas YL Lin11 месяцев назад

Coolll

Фото профиля Ziyang Xie
Ziyang Xie11 месяцев назад

Super cool. Does it outperform Map-Anything? And do you have any ideas of how we can handle dynamic (transient) objects within the input images.

Фото профиля Tengfei Wang
Tengfei Wang11 месяцев назад

It supports more outputs like splattings than mapanything. For point cloud, our visual quality is better. It is a good idea to perform some quantitative eval.

Фото профиля Peter MOUEZA🇲🇫
Peter MOUEZA🇲🇫11 месяцев назад

2D -> 3D

Фото профиля Brie Wensleydale🧀🐭
Brie Wensleydale🧀🐭11 месяцев назад

@bdsqlsz It's there a demo for this 'Render novel views using 3D Gaussians' function? That seems neat.

Фото профиля Psy
Psy11 месяцев назад

Can it also create fantasy environments?

Фото профиля CJ
CJ11 месяцев назад

How does it compare to triangle splatting?

Похожие видео

The training code for Hunyuan World 1.1 (WorldMirror) is released now!🔥🔥🔥 This release provides researchers and developers the full stack for customization and fine-tuning: 📷 Your video to 3D worlds in 1 second. 🪄ANY input (image, video, 3D prior) to ANY output (3DGS, depth, cameras, normal, points) Start customizing your model and exploring the demo! Online demo: Code:
0:20

The training code for Hunyuan World 1.1 (WorldMirror) is released now!🔥🔥🔥 This release provides researchers and developers the full stack for customization and fine-tuning: 📷 Your video to 3D worlds in 1 second. 🪄ANY input (image, video, 3D prior) to ANY output (3DGS, depth, cameras, normal, points) Start customizing your model and exploring the demo! Online demo: Code:

Tencent Hy

67,976 просмотров • 11 месяцев назад

⚡️Generating 3DGS scenes in 5 seconds on a single GPU⚡️ #FlashWorld enables ⚡️*fast*⚡️ (10~100x faster than previous methods) and 🔥*high-quality*🔥 3D world generation, from a single image or text prompt. Code: Page:
0:56

⚡️Generating 3DGS scenes in 5 seconds on a single GPU⚡️ #FlashWorld enables ⚡️*fast*⚡️ (10~100x faster than previous methods) and 🔥*high-quality*🔥 3D world generation, from a single image or text prompt. Code: Page:

Tengfei Wang

119,877 просмотров • 1 год назад

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇
1:30

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

Nikhil Keetha

123,641 просмотров • 1 год назад

Rewrite The Odyssey in your own playable game demo! No 3D modeling, no coding, just one image! With HappyOyster World Model, you can turn any image into an interactive game demo in seconds.
0:41

Rewrite The Odyssey in your own playable game demo! No 3D modeling, no coding, just one image! With HappyOyster World Model, you can turn any image into an interactive game demo in seconds.

HappyOyster

1,660,870 просмотров • 2 месяцев назад

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.
1:10

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

Superman

1,459,335 просмотров • 2 месяцев назад

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.
1:10

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

Yasir Ai

254,803 просмотров • 2 месяцев назад

This tool can learn any 3d spaces with just an image. It’s called OneCanvas, a NeurIPS 2026 Spotlight paper with public code and model. It merges video frames of a room into one panorama, so an ordinary image AI can answer questions about 3D space. → New state of the art on spatial reasoning benchmarks → Answers from any viewpoint, including the AI’s own position in the room → Needs depth data and camera positions, not just plain video 100% free & open-source.
0:44

This tool can learn any 3d spaces with just an image. It’s called OneCanvas, a NeurIPS 2026 Spotlight paper with public code and model. It merges video frames of a room into one panorama, so an ordinary image AI can answer questions about 3D space. → New state of the art on spatial reasoning benchmarks → Answers from any viewpoint, including the AI’s own position in the room → Needs depth data and camera positions, not just plain video 100% free & open-source.

Simplifying AI

18,608 просмотров • 6 дней назад

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)
0:20

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

126,142 просмотров • 1 год назад

Introducing CUT3R! An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!
0:34

Introducing CUT3R! An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!

Qianqian Wang

146,565 просмотров • 1 год назад

Midjourney-to-3D is now available! (Indeed, you can convert any 2D image to 3D) Please note that, for now, you'll need to manually set a depth map for your image in order to view its correct 3D version. (You can use to generate the depth map) But... stay tuned! We'll soon be offering instant 3D conversion for any image. *This is just an experimental version, and any feedback or videos of your results would be really interesting to see!
0:31

Midjourney-to-3D is now available! (Indeed, you can convert any 2D image to 3D) Please note that, for now, you'll need to manually set a depth map for your image in order to view its correct 3D version. (You can use to generate the depth map) But... stay tuned! We'll soon be offering instant 3D conversion for any image. *This is just an experimental version, and any feedback or videos of your results would be really interesting to see!

Cristian Peñas ░░░░░░░░

445,471 просмотров • 3 лет назад

Depth is starting to feel less like an image… and more like geometry. InfiniDepth (open source) pushes exactly in that direction🤩 Depth is no longer just a map. It’s becoming a geometry representation. Single image → depth → 3DGS🥳 It’s not replacing real-world capture, but it’s definitely changing how image-to-3D works.
0:25

Depth is starting to feel less like an image… and more like geometry. InfiniDepth (open source) pushes exactly in that direction🤩 Depth is no longer just a map. It’s becoming a geometry representation. Single image → depth → 3DGS🥳 It’s not replacing real-world capture, but it’s definitely changing how image-to-3D works.

KIRI Engine - 3D Scanner App

26,777 просмотров • 6 месяцев назад

🚨 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 environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄
3:52

🚨 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 environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,340 просмотров • 1 месяц назад

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.
0:24

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Xiao-Xiao Long

31,305 просмотров • 2 лет назад

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at
0:51

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

World Labs

117,588 просмотров • 11 месяцев назад

📸 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
1:03

📸 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

23,176 просмотров • 2 месяцев назад

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.
1:20

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

Ceyuan Yang

32,971 просмотров • 5 месяцев назад

🚀 Just created something completely new! I Rewrote Apple's Sharp to generate 3D Gaussian Splats from a single 360° equirectangular image made from FLUX 2 (Flex) One equirectangular image → Full spherical 3DGS world! ✨ New web interface - drag & drop your pano, select quality, download PLY ⚡ 2-3 sec on a older laptop Quality tiers: ▫️ Low: 500K splats ▫️ Medium: 2M splats ▫️ High: 4.7M splats ▫️ Ultra: 8.4M splats The pipeline: 360° depth estimation from equirectangular input Spherical projection maps pixels → 3D points Each point becomes a Gaussian with depth-scaled radius - Export to standard PLY for any 3DGS viewer (Unity) No multi-view capture. No COLMAP. No NeRF training. Just upload a pano, pick quality, get your splats. #3DGS #GaussianSplatting #ComputerVision #AI #madewithunity #Splats Sharp Monocular View Synthesis in Less Than a Second
0:27

🚀 Just created something completely new! I Rewrote Apple's Sharp to generate 3D Gaussian Splats from a single 360° equirectangular image made from FLUX 2 (Flex) One equirectangular image → Full spherical 3DGS world! ✨ New web interface - drag & drop your pano, select quality, download PLY ⚡ 2-3 sec on a older laptop Quality tiers: ▫️ Low: 500K splats ▫️ Medium: 2M splats ▫️ High: 4.7M splats ▫️ Ultra: 8.4M splats The pipeline: 360° depth estimation from equirectangular input Spherical projection maps pixels → 3D points Each point becomes a Gaussian with depth-scaled radius - Export to standard PLY for any 3DGS viewer (Unity) No multi-view capture. No COLMAP. No NeRF training. Just upload a pano, pick quality, get your splats. #3DGS #GaussianSplatting #ComputerVision #AI #madewithunity #Splats Sharp Monocular View Synthesis in Less Than a Second

Daniel Skaale

74,395 просмотров • 9 месяцев назад

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:
1:20

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,848 просмотров • 11 месяцев назад