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。

Made an interactive shader to visualize our models of space-time curvature in 3D, as a lattice. Similar visualizations are typically 2D grids, and I wanted something more complete/robust/accurate.

Mirza Beig

29,201 subscribers

104,623 次观看 • 9 个月前 •via X (Twitter)

教育科学技术

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

I want to do my absolute best to provide something similar to a live2D customizable model but for 3D!🩷 2D models are so amazing. They have so many clothing sliders, and now, 3D can too!✨Now, our clothes can have even more customization possibilities! -^u^-

I want to do my absolute best to provide something similar to a live2D customizable model but for 3D!🩷 2D models are so amazing. They have so many clothing sliders, and now, 3D can too!✨Now, our clothes can have even more customization possibilities! -^u^-

Pastell & Palette🤍 3D Customizable Model!

27,584 次观看 • 7 个月前

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Been pushing Rive's new 3D and shader support to see what's possible 🚀 Using AI + scripting, I was able to: • Import 3D models • Generate cameras and lights • Create custom shaders (wireframe, AO, sketch, toon) • Build materials • Project animated textures onto 3D geometry • Place 2D components directly in 3D space It's pretty wild to see how quickly Rive is evolving into a true all-in-one platform for interactive design.

Sanu Sagar

18,218 次观看 • 4 个月前

We built an interactive 3D model of our solar system to teach kids about space. Based on NASA's JPL data to within 1/60 of a degree. It runs in real time. Made for Marble App.

We built an interactive 3D model of our solar system to teach kids about space. Based on NASA's JPL data to within 1/60 of a degree. It runs in real time. Made for Marble App.

Lionel Mora

21,056 次观看 • 2 个月前

Gemini can now transform your questions and complex concepts into customizable interactive visualizations directly in your chat. Adjust variables, rotate 3D models, and explore data for a more immersive way to learn and explore in Gemini.

Gemini can now transform your questions and complex concepts into customizable interactive visualizations directly in your chat. Adjust variables, rotate 3D models, and explore data for a more immersive way to learn and explore in Gemini.

Google Gemini

5,889,653 次观看 • 5 个月前

Made a UI to visualize multiple AI agents playing as different civilizations, each navigating its own decision tree Most agent workflow UIs are pretty static, so I wanted to build something that feels more dynamic and fun to explore

Made a UI to visualize multiple AI agents playing as different civilizations, each navigating its own decision tree Most agent workflow UIs are pretty static, so I wanted to build something that feels more dynamic and fun to explore

Dilum Sanjaya

124,083 次观看 • 3 个月前

Volumetric, animated 3D noise shader block in Unity. Where each frame is 2D space, and the 3rd dimension is time. So that, measurement of change within a slice is 'space', and measurement of change across slices is 'time'. As a 3D block, you see the noise animate into the 3rd dimension, but when looking at only a single slice, it appears to evolve in place. Likewise, for 4D... If: this were 3D noise, then: the 4th dimension would be whatever processing/frames/states of 3D data.

Volumetric, animated 3D noise shader block in Unity. Where each frame is 2D space, and the 3rd dimension is time. So that, measurement of change within a slice is 'space', and measurement of change across slices is 'time'. As a 3D block, you see the noise animate into the 3rd dimension, but when looking at only a single slice, it appears to evolve in place. Likewise, for 4D... If: this were 3D noise, then: the 4th dimension would be whatever processing/frames/states of 3D data.

Mirza Beig

126,907 次观看 • 9 个月前

Imagine having an idea for a space game… and actually being able to start building it . I wanted to test what an AI-powered game creation workflow could look like. MeshyAI helped create spacecraft models, and GPT 6 Astra helped bring those assets into an interactive space environment. The coolest part for me is seeing individual 3D models become part of something bigger. A ship is cool. A whole universe built around those ships is even cooler. #Astra #MeshyAI #GameDev #AI3D

Imagine having an idea for a space game… and actually being able to start building it . I wanted to test what an AI-powered game creation workflow could look like. MeshyAI helped create spacecraft models, and GPT 6 Astra helped bring those assets into an interactive space environment. The coolest part for me is seeing individual 3D models become part of something bigger. A ship is cool. A whole universe built around those ships is even cooler. #Astra #MeshyAI #GameDev #AI3D

Isabella

41,565 次观看 • 21 天前

🆕 Fresh coat of paint to Code Blocks in @ChatGPTapp ! I esp like using them for in-chat data visualizations - Code Blocks natively support mermaid diagrams, vega, HTML, React, with more 🔜 This is an early launch as we make this a more interactive and useful part of ChatGPT

🆕 Fresh coat of paint to Code Blocks in @ChatGPTapp ! I esp like using them for in-chat data visualizations - Code Blocks natively support mermaid diagrams, vega, HTML, React, with more 🔜 This is an early launch as we make this a more interactive and useful part of ChatGPT

Justin

418,913 次观看 • 7 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

Excited to share a new vibe coded prototype: an interactive lesson on ants and their habitat, designed for elementary school students. AI allowed me to finalize this demo quickly. Some educational details still need review, but the main chambers of an anthill are all represented. Everything was made in Omma AI , a Spline product. What's inside: - 3D models created with Omma, all I needed was one image of the anthill's exterior and another of its cross-section to generate both 3D models - Clouds done with sprites - A custom shader mask to reveal the inside of the anthill This was a really fun one to work on!

Excited to share a new vibe coded prototype: an interactive lesson on ants and their habitat, designed for elementary school students. AI allowed me to finalize this demo quickly. Some educational details still need review, but the main chambers of an anthill are all represented. Everything was made in Omma AI , a Spline product. What's inside: - 3D models created with Omma, all I needed was one image of the anthill's exterior and another of its cross-section to generate both 3D models - Clouds done with sprites - A custom shader mask to reveal the inside of the anthill This was a really fun one to work on!

Joseph Azar

19,890 次观看 • 4 个月前

After 7 months of working on this project, the Super Mario Bros. Z Intro 3D Remake is complete! This animation has been something I've been wanting to make for a long time! I hope you enjoy it! Credits: -Mettalix Rig: kimo -Fire Shader: Simon Thommes Models Resource

After 7 months of working on this project, the Super Mario Bros. Z Intro 3D Remake is complete! This animation has been something I've been wanting to make for a long time! I hope you enjoy it! Credits: -Mettalix Rig: kimo -Fire Shader: Simon Thommes Models Resource

NooB.

1,924,807 次观看 • 3 年前

This is some of our prototyping footage as we tried to figure out how to render 2D gameplay onto an object in a 3D space. It's actually the same book in the final game! If you'd like to hear about how we made The Plucky Squire, let us know in the comments ✍️

This is some of our prototyping footage as we tried to figure out how to render 2D gameplay onto an object in a 3D space. It's actually the same book in the final game! If you'd like to hear about how we made The Plucky Squire, let us know in the comments ✍️

The Plucky Squire 📖

52,542 次观看 • 2 年前

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 次观看 • 3 年前

Explore the shallow seas as a stingray, vibe coded on ThreeJs using Cursor. I made a similar game more than a year ago, but I hit a roadblock because the models back then (I think I was using Sonnet 3.5) struggled with handling 3D models, but now, it's a different story. All 3D models were made with Tripo3D and I was able to put this together in less than 8 hours worth of work. I mainly used Composer 2.5 and Opus 4.8 to make this. Will try to find the original game I made a while ago and put it into the replies section.

Explore the shallow seas as a stingray, vibe coded on ThreeJs using Cursor. I made a similar game more than a year ago, but I hit a roadblock because the models back then (I think I was using Sonnet 3.5) struggled with handling 3D models, but now, it's a different story. All 3D models were made with Tripo3D and I was able to put this together in less than 8 hours worth of work. I mainly used Composer 2.5 and Opus 4.8 to make this. Will try to find the original game I made a while ago and put it into the replies section.

Danny Limanseta

35,346 次观看 • 3 个月前

Wanted to try making an in-game cutscene in UEFN to tell the story of The Kraken. Since there’s no way to animate in 2D in UEFN, I went old-school and made a few 3D planes with masked materials and cut up the layers in Photoshop. Fortnite Developers #Fortnite #UEFN #FortniteCreative

Wanted to try making an in-game cutscene in UEFN to tell the story of The Kraken. Since there’s no way to animate in 2D in UEFN, I went old-school and made a few 3D planes with masked materials and cut up the layers in Photoshop. Fortnite Developers #Fortnite #UEFN #FortniteCreative

Joel Best

66,171 次观看 • 1 年前

😰Tired of spending hours on complex hard-surface models? Toolbag 5’s new Bevel shader is here to simplify your workflow! Add smooth edges to your objects for a more realistic look while reducing modeling time. Also, bake bevels into Ambient Occlusion and Curvature maps!

😰Tired of spending hours on complex hard-surface models? Toolbag 5’s new Bevel shader is here to simplify your workflow! Add smooth edges to your objects for a more realistic look while reducing modeling time. Also, bake bevels into Ambient Occlusion and Curvature maps!

Marmoset

121,047 次观看 • 2 年前

This AI created an interactive 3D textbook !! 💀 I didn't manually create any of these 3d models I built it using: 👉 GPT-6 Astra 👉 Hyper3D Rodin's MCP Hyper3D worked on the 3D Models And GPT-6 Astra made the website with the 3D Models integrated to the UI controls. It even added floating labels for the HEART !! This is what happens when an AI can actually CREATE 3D assets 👇

This AI created an interactive 3D textbook !! 💀 I didn't manually create any of these 3d models I built it using: 👉 GPT-6 Astra 👉 Hyper3D Rodin's MCP Hyper3D worked on the 3D Models And GPT-6 Astra made the website with the 3D Models integrated to the UI controls. It even added floating labels for the HEART !! This is what happens when an AI can actually CREATE 3D assets 👇

SARAH

135,934 次观看 • 21 天前

One thing I really envy about 2D vtubers is how their models sway so beautifully! :D So, like a normal person, I built my own system to replicate a similar effect for our 3D customizable vtuber model!💜 It looks kind of uncanny to see a 3D model moving like a Live2D one hehe✨

One thing I really envy about 2D vtubers is how their models sway so beautifully! :D So, like a normal person, I built my own system to replicate a similar effect for our 3D customizable vtuber model!💜 It looks kind of uncanny to see a 3D model moving like a Live2D one hehe✨

Pastell & Palette🤍 3D Customizable Model!

36,323 次观看 • 3 个月前

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

trungduyng

34,849 次观看 • 1 年前

Is this a 3D model? look man, it's like, i advanced my shader engine in the time it took you to reply. would have probably taken an entire team of AAA gaming's best idiots to do this before. now we can do it in two prompts. WeEeEeeEeE! 3D models WeeEee! 😂

Is this a 3D model? look man, it's like, i advanced my shader engine in the time it took you to reply. would have probably taken an entire team of AAA gaming's best idiots to do this before. now we can do it in two prompts. WeEeEeeEeE! 3D models WeeEee! 😂

Satoshi Nakamoto, Andrew Rulnick

244,935 次观看 • 10 个月前