Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

⚡️ 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

1,168 subscribers

126,142 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

44 Kommentare

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Project page: Arxiv: A huge shout out to my absolutely incredible co-authors @jasonyzhang2 @_pratul_ @RuiqiGao @ArthurBrussee @holynski_ @rmbrualla @jon_barron @philipphenzler (2/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Generating 3D content is challenging because (1) It is unclear how to represent and structure (possibly unbounded) 3D scene data for diffusion models. (2) 3D data is much more limited than 2D image and video data. (3/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Bolt3D puts 3D data in 2D grids (remember Splatter Images?). First, we sample multi-view images and pointmaps with a latent diffusion model. Then, the properties of 3D Gaussians are estimated with a Gaussian head. We reconstruct a large dataset of 3D scenes for training. (4/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

The key to generating high-quality geometry with a latent diffusion is to train a VAE for geometry data (pointmaps). We found that, for geometry data, our transformer decoder is more appropriate than a convolutional decoder, and that RGB image VAEs fail catastrophically. (5/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Bolt3D can accept variable number of input images. Our model adheres to conditioning when it is available and generates unobserved scene regions without any re-projection or in-painting mechanisms. (6/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Bolt3D enables generative capabilities in feed-forward 3D reconstructors. Compared to SOTA optimization-based pipelines (first generate Novel Views, then distill 3D), Bolt3D reduces inference cost by 64-300x. (7/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Check out the generated 3D scenes in our interactive viewer, powered by Brush, as well as more video results on the project website! (8/9)

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Finally, a special thank you to @poolio for his helpful suggestions, guidance and contributions! (9/9)

Profilbild von clem 🤗

clem 🤗vor 1 Jahr

would be so cool to have a to try!

Profilbild von Matthias Niessner

Matthias Niessnervor 1 Jahr

Great work!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thank you!

Profilbild von Hang Gao

Hang Gaovor 1 Jahr

Nice work!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thank you!

Profilbild von Jensen Zhou

Jensen Zhouvor 1 Jahr

@hangg70 Hi y'all, let me introduce you two.

Profilbild von Hang Gao

Hang Gaovor 1 Jahr

@StanSzymanowicz Amesome!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

@jensenzhoujh The two camera-conditioned-NVS experts!

Profilbild von Qianyi Wu

Qianyi Wuvor 1 Jahr

Impressive results!

Profilbild von Abdullah Hamdi

Abdullah Hamdivor 1 Jahr

Amazing !

Profilbild von Samarth Sinha

Samarth Sinhavor 1 Jahr

Congrats Stan!!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thanks Sam!

Profilbild von Arjun Karpur

Arjun Karpurvor 1 Jahr

Congrats on the release, Stan!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thanks Arjun!

Profilbild von Markus Malmros

Markus Malmrosvor 1 Jahr

Wow, looks really cool!

Profilbild von tipatat

tipatatvor 1 Jahr

Really impressive work! Would it be possible to improve the quality with a large data set of high quality 3DGS made of real world capture?

Profilbild von Nataniel Ruiz

Nataniel Ruizvor 1 Jahr

amazing

Profilbild von Hirokatsu Kataoka | 片岡裕雄

Hirokatsu Kataoka | 片岡裕雄vor 1 Jahr

Amazing tech, congratulations Stan! 🎉

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thanks Hirokatsu!

Profilbild von Bilawal Sidhu

Bilawal Sidhuvor 1 Jahr

Very cool results, congrats!

Profilbild von Haofei Xu

Haofei Xuvor 1 Jahr

Fantastic results! Congrats!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thanks Haofei!

Profilbild von Rundi Wu

Rundi Wuvor 1 Jahr

Great work and awesome results! Congrats Stan!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thanks Rundi!

Profilbild von Nikita Karaev

Nikita Karaevvor 1 Jahr

Super cool! Congrats Stan!

Profilbild von Stan Szymanowicz

Stan Szymanowiczvor 1 Jahr

Thank you Nikita!

Profilbild von BLd

BLdvor 1 Jahr

Congrats, results are outstanding!

Profilbild von :3

:3vor 1 Jahr

In 2020 I made a framework that can generate cities at ~10 million vertices in 16.667ms, meaning that you can generate a whole game map 60 times per second while playing the game, and everything is fully interactive and hierarchically laid out:

Profilbild von Kosta Derpanis at #ECCV2026 🇸🇪

Kosta Derpanis at #ECCV2026 🇸🇪vor 1 Jahr

💪

Profilbild von TOTORITO

TOTORITOvor 1 Jahr

Waaawwww !!!

Profilbild von The Qubits Guy

The Qubits Guyvor 1 Jahr

When will @Apple license your tech for my next iPhone?

Profilbild von MOTA

MOTAvor 1 Jahr

release the kraken

Profilbild von MangoMagic™️

MangoMagic™️vor 1 Jahr

Fascinating tech or just a new way to procrastinate? #3DJustGotReal #WhereIsMyGPU #ProcrastinationStation

Profilbild von iKrasinski

iKrasinskivor 1 Jahr

Amazing. Waiting for the HF space to feel with my hands.

Profilbild von Simsalabim

Simsalabimvor 1 Jahr

Congrats, looks great! Any Plans on releasing the code? Would love to try it out!

Profilbild von Diego Bonati

Diego Bonativor 1 Jahr

looks very interesting, I would like to generate stereoscopic images with this and also VR equirectangular format.

Ähnliche Videos

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,241 Aufrufe • vor 2 Jahren

🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors Aleksander Holynski, Ben Poole and an amazing team!

🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors Aleksander Holynski, Ben Poole and an amazing team!

Ruiqi Gao

153,337 Aufrufe • vor 2 Jahren

⚡️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:

⚡️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 Aufrufe • vor 1 Jahr

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.

Dreaming Tulpa 🥓👑

85,161 Aufrufe • vor 1 Jahr

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

World Labs

342,124 Aufrufe • vor 1 Jahr

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 Aufrufe • vor 3 Jahren

Apple drops a new 3D model generator, LiTo > Learns geometry + appearance together in a unified 3D latent space > Turns RGB-D images into a compact surface light field > Recreates specular highlights under complex lighting > Generates 3D objects from a single image with input-consistent materials Big step toward more realistic 3D generation

Apple drops a new 3D model generator, LiTo > Learns geometry + appearance together in a unified 3D latent space > Turns RGB-D images into a compact surface light field > Recreates specular highlights under complex lighting > Generates 3D objects from a single image with input-consistent materials Big step toward more realistic 3D generation

AI Search

13,078 Aufrufe • vor 5 Monaten

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Stability AI

197,625 Aufrufe • vor 1 Jahr

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

0xMarioNawfal

47,559 Aufrufe • vor 3 Monaten

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

218,904 Aufrufe • vor 5 Tagen

DimensionX Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

DimensionX Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

AK

58,273 Aufrufe • vor 2 Jahren

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

36,110 Aufrufe • vor 1 Jahr

⚡️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:

⚡️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:

Tengfei Wang

67,403 Aufrufe • vor 1 Jahr

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,960 Aufrufe • vor 1 Jahr

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:

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

168,996 Aufrufe • vor 1 Jahr

We made an interactive client-server viewer for LagerNVS with Jonathon Luiten! You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser. Check out the video below for some spaces I recently captured in Oxford, London and beyond!

We made an interactive client-server viewer for LagerNVS with Jonathon Luiten! You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser. Check out the video below for some spaces I recently captured in Oxford, London and beyond!

Stan Szymanowicz

17,428 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 6 Monaten

#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 Aufrufe • vor 1 Jahr

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

Bowen Wen

77,313 Aufrufe • vor 10 Monaten