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。

Earlier this year, we launched 4D Generation with mesh-based schemas like the car-5. Now, we're expanding to 30+ new schemas powered by Procedural Model Generation. This shift allows for fully functional and editable 3D assets—from submarines that dive to jet planes that fly. Here's a sneak peek of what's... show more

David Baszucki

542,532 subscribers

141,339 次观看 • 4 个月前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Today, we’re launching 4D generation, powered by our Cube Foundation Model. Creators can build experiences that let players create interactive 3D objects like cars, planes, and more. This is just the beginning, see what's next with AI-powered creation. 1/4

Today, we’re launching 4D generation, powered by our Cube Foundation Model. Creators can build experiences that let players create interactive 3D objects like cars, planes, and more. This is just the beginning, see what's next with AI-powered creation. 1/4

Roblox

1,590,470 次观看 • 7 个月前

Here's a little sneak peek of something we're aiming to ship this week in Basecamp 5. Zoom the center column on home to go full screen with project cards. Better optimized for people with larger screens, and similar to a view we had in BC4 for those who are used to that. Coming soon!

Here's a little sneak peek of something we're aiming to ship this week in Basecamp 5. Zoom the center column on home to go full screen with project cards. Better optimized for people with larger screens, and similar to a view we had in BC4 for those who are used to that. Coming soon!

Jason Fried

26,765 次观看 • 3 个月前

Hitem3D V2.0 just launched. It's an AI 3D model generation tool that does three things: - Photo or image to full 3D model - Model segmentation so you can isolate and refine parts - Image to STL for 3D printing Combine this with Google Nano Banana and you can build game assets, product prototypes, and printable designs in minutes. Here's what I tested. Sponsored by Hi3D 1/4

Hitem3D V2.0 just launched. It's an AI 3D model generation tool that does three things: - Photo or image to full 3D model - Model segmentation so you can isolate and refine parts - Image to STL for 3D printing Combine this with Google Nano Banana and you can build game assets, product prototypes, and printable designs in minutes. Here's what I tested. Sponsored by Hi3D 1/4

AshutoshShrivastava

19,616 次观看 • 6 个月前

Reunited with the Windows Terminal devs and we're cooking up something new. Here's a sneak peek of installing a winget package through a new utility coming soon to PowerToys: P.S. this is live working code, courtesy of Mike Griese 😉

Reunited with the Windows Terminal devs and we're cooking up something new. Here's a sneak peek of installing a winget package through a new utility coming soon to PowerToys: P.S. this is live working code, courtesy of Mike Griese 😉

Kayla Cinnamon ☕

12,860 次观看 • 1 年前

📢 A Sneak Peek: Auto-Rigging on NeuralAI! Get ready to be amazed! Our fearless bald developer just dropped a sneak peek of the next NeuralAI model, but that's not all! We're also testing a groundbreaking new feature: auto-rigging! What's auto-rigging? It's like adding a skeleton to your 3D model, allowing for animation. Currently, rigging is a time-consuming task for many game developers. Imagine the possibilities if it could be done automatically! This potential feature could significantly streamline the 3D creation process, saving animators valuable time and resources. This sneak peek offers a glimpse into the future of NeuralAI. Our commitment to innovation extends beyond creating stunning 3D assets – we're striving to streamline the entire 3D creation workflow. Stay tuned for further updates!

📢 A Sneak Peek: Auto-Rigging on NeuralAI! Get ready to be amazed! Our fearless bald developer just dropped a sneak peek of the next NeuralAI model, but that's not all! We're also testing a groundbreaking new feature: auto-rigging! What's auto-rigging? It's like adding a skeleton to your 3D model, allowing for animation. Currently, rigging is a time-consuming task for many game developers. Imagine the possibilities if it could be done automatically! This potential feature could significantly streamline the 3D creation process, saving animators valuable time and resources. This sneak peek offers a glimpse into the future of NeuralAI. Our commitment to innovation extends beyond creating stunning 3D assets – we're striving to streamline the entire 3D creation workflow. Stay tuned for further updates!

NeuralAI

45,170 次观看 • 2 年前

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

📣 New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end, producing results that are superior to existing solutions — at 3-10x the speed of existing work in this space. Details in the technical report ➡️

AI at Meta

408,949 次观看 • 2 年前

[NeurIPS '24] DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation Abstract (excerpt) We introduce DreamMesh4D, a novel framework that combines mesh representation with sparse-controlled deformation technique to generate high-quality 4D object from a monocular video. To overcome the limitation of classical texture representation, we bind Gaussian splats to the surface of the triangular mesh for differentiable optimization of both the texture and mesh vertices. In particular, DreamMesh4D begins with a coarse mesh provided by a single image based 3D generation method. Sparse points are then uniformly sampled across the surface of the mesh, and are used to build a deformation graph to drive the motion of the 3D object for the sake of computational efficiency and providing additional constraint. For each step, transformations of sparse control points are predicted using a deformation network, and the mesh vertices as well as the bound surface Gaussians are deformed via a geometric skinning algorithm. The skinning algorithm is a hybrid approach combining LBS (linear blending skinning) and DQS (dual-quaternion skinning), mitigating drawbacks associated with both approaches. The static surface Gaussians and mesh vertices as well as the dynamic deformation network are learned via reference view photometric loss, score distillation loss as well as other regularization losses in a two-stage manner. Extensive experiments demonstrate that our method outperforms prior video-to-4D generation methods in terms of rendering quality and spatial-temporal consistency.

[NeurIPS '24] DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation Abstract (excerpt) We introduce DreamMesh4D, a novel framework that combines mesh representation with sparse-controlled deformation technique to generate high-quality 4D object from a monocular video. To overcome the limitation of classical texture representation, we bind Gaussian splats to the surface of the triangular mesh for differentiable optimization of both the texture and mesh vertices. In particular, DreamMesh4D begins with a coarse mesh provided by a single image based 3D generation method. Sparse points are then uniformly sampled across the surface of the mesh, and are used to build a deformation graph to drive the motion of the 3D object for the sake of computational efficiency and providing additional constraint. For each step, transformations of sparse control points are predicted using a deformation network, and the mesh vertices as well as the bound surface Gaussians are deformed via a geometric skinning algorithm. The skinning algorithm is a hybrid approach combining LBS (linear blending skinning) and DQS (dual-quaternion skinning), mitigating drawbacks associated with both approaches. The static surface Gaussians and mesh vertices as well as the dynamic deformation network are learned via reference view photometric loss, score distillation loss as well as other regularization losses in a two-stage manner. Extensive experiments demonstrate that our method outperforms prior video-to-4D generation methods in terms of rendering quality and spatial-temporal consistency.

MrNeRF

12,323 次观看 • 1 年前

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Felix Heide

27,779 次观看 • 1 年前

No, your eyes aren’t playing tricks on you. That’s a horizontal timeline in the Interactions panel (COMING SOON) 😍 ICYMI, we hosted an announcement video with Cassie Evans, Web Bae, and rachel wolan to dive in to all things GSAP (which is now 100% free for everyone!) and give you a preview of what's to come with the next generation of Webflow Interactions powered by GSAP. Give it a watch here:

No, your eyes aren’t playing tricks on you. That’s a horizontal timeline in the Interactions panel (COMING SOON) 😍 ICYMI, we hosted an announcement video with Cassie Evans, Web Bae, and rachel wolan to dive in to all things GSAP (which is now 100% free for everyone!) and give you a preview of what's to come with the next generation of Webflow Interactions powered by GSAP. Give it a watch here:

Webflow

20,985 次观看 • 1 年前

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 次观看 • 2 年前

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models paper page: Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models paper page: Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.

AK

117,068 次观看 • 2 年前

Happy New Year, from your friends at TCM 🎉 We thank our fans as we honored our 30th anniversary this year, and we're so excited to share what's in store for 2025! From the movies to the memories, here's to celebrating the classics with all of you. 🥂

Happy New Year, from your friends at TCM 🎉 We thank our fans as we honored our 30th anniversary this year, and we're so excited to share what's in store for 2025! From the movies to the memories, here's to celebrating the classics with all of you. 🥂

TCM

30,399 次观看 • 1 年前

Since we launched our free of charge tier, we've been SO inspired by your creations (and want to see even more). So for a limited time, we're expanding monthly credits for the free tier from 100 to 180. Hopefully this enables new & existing users to explore what's possible in Flow!

Since we launched our free of charge tier, we've been SO inspired by your creations (and want to see even more). So for a limited time, we're expanding monthly credits for the free tier from 100 to 180. Hopefully this enables new & existing users to explore what's possible in Flow!

Google Flow

43,559 次观看 • 10 个月前

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

AK

38,853 次观看 • 2 年前

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 次观看 • 1 年前

This promo was peak. 🔥 Seth Rollins: “We came into this company together through that crowd. We kicked out the old generation. Just like we did when we came in—young, hungry, and ready to take over. Now there's a new generation of young men and women who are going to do the same thing to us.” What a beautiful promo by Seth. ❤️

This promo was peak. 🔥 Seth Rollins: “We came into this company together through that crowd. We kicked out the old generation. Just like we did when we came in—young, hungry, and ready to take over. Now there's a new generation of young men and women who are going to do the same thing to us.” What a beautiful promo by Seth. ❤️

A L L D A Y 🚀

20,619 次观看 • 2 个月前

Another small test of Krea from Krea. Impressed with the speed of the generation, and the new style slider that will make it easier to generate images that stick much more closely to the input. In this case though, just a material test. More tests of the style slider in effect soon. Nvidia's CEO Jensen Huang said that "Every single pixel will be generated soon. Not rendered: generated". We're getting there. #ai #3d

Another small test of Krea from Krea. Impressed with the speed of the generation, and the new style slider that will make it easier to generate images that stick much more closely to the input. In this case though, just a material test. More tests of the style slider in effect soon. Nvidia's CEO Jensen Huang said that "Every single pixel will be generated soon. Not rendered: generated". We're getting there. #ai #3d

Martin Nebelong

22,217 次观看 • 2 年前

#Roblox #RobloxDev Update on the plugin Roblox added all the features required to make it useful! You can now save Editable Images to assets 🥳 Unfortunately the latest changes also involve a permission check that only allows you to turn your own assets into Editable Images ☹️. Lets hope an exception gets added for Plugin / Studio use so that people can apply adjustments to images that are publicly available Still a really good feature, I will be releasing this plugin as soon as Editable Images and the CreateAssetAsync function are out of beta!

#Roblox #RobloxDev Update on the plugin Roblox added all the features required to make it useful! You can now save Editable Images to assets 🥳 Unfortunately the latest changes also involve a permission check that only allows you to turn your own assets into Editable Images ☹️. Lets hope an exception gets added for Plugin / Studio use so that people can apply adjustments to images that are publicly available Still a really good feature, I will be releasing this plugin as soon as Editable Images and the CreateAssetAsync function are out of beta!

Imed

23,798 次观看 • 1 年前