Загрузка видео...

Не удалось загрузить видео

На главную

Just made Pascal's item catalog infinite. Pulling 3D objects straight out of images, live in the browser. SAM 3D Objects + Three.js + WebGPU. 👇

wawasensei's profile picture

Wawa Sensei

6,377 subscribers

46,888 просмотров • 5 месяцев назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models: 🛋️ SAM 3D Objects for object and scene reconstruction 🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions. 🔗 Learn more:
0:50

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models: 🛋️ SAM 3D Objects for object and scene reconstruction 🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions. 🔗 Learn more:

AI at Meta

861,526 просмотров • 10 месяцев назад

3D Congealing 3D-Aware Image Alignment in the Wild We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images capturing semantically similar objects. Given a collection of unlabeled Internet images, our goal is to associate the shared semantic parts
0:25

3D Congealing 3D-Aware Image Alignment in the Wild We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images capturing semantically similar objects. Given a collection of unlabeled Internet images, our goal is to associate the shared semantic parts

AK

16,325 просмотров • 2 лет назад

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:
1:54

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 просмотров • 10 месяцев назад

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.
0:28

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 просмотров • 2 лет назад

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.
0:26

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.

Krea

666,228 просмотров • 1 год назад

3D illustration of the working principles of everyday objects around us
1:03

3D illustration of the working principles of everyday objects around us

Hub4Learning

1,103,044 просмотров • 9 месяцев назад

Today we’re excited to unveil a new generation of Segment Anything Models: 1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. 🔗 Learn more about SAM 3: 2️⃣ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. 🔗 Learn more about SAM 3D: These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.
0:34

Today we’re excited to unveil a new generation of Segment Anything Models: 1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. 🔗 Learn more about SAM 3: 2️⃣ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. 🔗 Learn more about SAM 3D: These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.

AI at Meta

1,091,560 просмотров • 10 месяцев назад

How good is Tencent HY 3D 2.1 - Tencent’s new generative 3D model? Honestly, it’s impressive. I generated these 16 objects and rendered them in Blender, check out the results below! 👇
0:56

How good is Tencent HY 3D 2.1 - Tencent’s new generative 3D model? Honestly, it’s impressive. I generated these 16 objects and rendered them in Blender, check out the results below! 👇

Emm | scenario.com

43,157 просмотров • 1 год назад

Studying offline 3D vibe-coding with Three.js: - Gemma 4 E4B runs on-device via llama.cpp (or in-browser via transformers.js, ~13x slower). - Scene renders through WebGPU→Dawn→Metal. - A grammar + verifier outside the weights makes the model reliable at Three.js.
0:23

Studying offline 3D vibe-coding with Three.js: - Gemma 4 E4B runs on-device via llama.cpp (or in-browser via transformers.js, ~13x slower). - Scene renders through WebGPU→Dawn→Metal. - A grammar + verifier outside the weights makes the model reliable at Three.js.

Renaud

13,101 просмотров • 3 месяцев назад

An infinite canvas of gaming merch, every item pulled live from the Shopify Catalog API. You can just build things
1:41

An infinite canvas of gaming merch, every item pulled live from the Shopify Catalog API. You can just build things

Alex ElChehimi

17,230 просмотров • 3 месяцев назад

Turntable is now in the #AdobeIllustrator beta! Rotate vector objects as if they’re 3D.
0:43

Turntable is now in the #AdobeIllustrator beta! Rotate vector objects as if they’re 3D.

Paul Trani

16,920 просмотров • 1 год назад

Introducing the TapNow x Marble WORLD Model! Transform static images into explorable environments with infinite angularity. The 3D redraw feature allows you to reimagine and transform objects within the generated space. Click the link below for more details.
0:42

Introducing the TapNow x Marble WORLD Model! Transform static images into explorable environments with infinite angularity. The 3D redraw feature allows you to reimagine and transform objects within the generated space. Click the link below for more details.

TapNow

2,652,996 просмотров • 5 месяцев назад

Our voxel engine rendering technique heavily uses levels of details to try and keep high performance in the browser! Made with Three.js on #webgpu
0:30

Our voxel engine rendering technique heavily uses levels of details to try and keep high performance in the browser! Made with Three.js on #webgpu

AresRPG - The Sui MMORPG

14,893 просмотров • 3 месяцев назад

Step into a new era of creation. With Cube 3D, turn simple text prompts into 3D objects in seconds. What will you build?
0:44

Step into a new era of creation. With Cube 3D, turn simple text prompts into 3D objects in seconds. What will you build?

Roblox

1,062,515 просмотров • 1 год назад

Introducing Objaverse-XL, an open dataset of over 10 million 3D objects! With it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: 🧵👇 📝 Paper:
0:53

Introducing Objaverse-XL, an open dataset of over 10 million 3D objects! With it, we train Zero123-XL, a foundation model for 3D, observing incredible 3D generalization abilities: 🧵👇 📝 Paper:

Matt Deitke

368,813 просмотров • 3 лет назад

A close up look at the nozzle of a 3D Printer & how it "prints" objects.
1:13

A close up look at the nozzle of a 3D Printer & how it "prints" objects.

HOW THINGS WORK

113,928 просмотров • 1 год назад

Made some improvements to my #threejs pipeline and shader editor, with render passes. Also, direct import of 3d Objects from glTF.
0:30

Made some improvements to my #threejs pipeline and shader editor, with render passes. Also, direct import of 3d Objects from glTF.

Palash Bansal

55,327 просмотров • 2 лет назад

🌍 What if the entire Earth could be streamed as a photorealistic 3D world? This prototype renders billions of 3D Gaussian splats directly in the browser. Powered by PlayCanvas . WebGPU + WebGL. The technology is ready. The remaining challenge is capturing the planet. 👇
1:05

🌍 What if the entire Earth could be streamed as a photorealistic 3D world? This prototype renders billions of 3D Gaussian splats directly in the browser. Powered by PlayCanvas . WebGPU + WebGL. The technology is ready. The remaining challenge is capturing the planet. 👇

Martin Valigursky

20,427 просмотров • 4 месяцев назад

600MB of photoreal 3D streamed to your web browser in seconds. 🌐 This abandoned Czech textile factory is a 3D Gaussian splat running on the PlayCanvas engine. WebGPU + Streamed SOG + Voxel Collision. [1/2]
0:27

600MB of photoreal 3D streamed to your web browser in seconds. 🌐 This abandoned Czech textile factory is a 3D Gaussian splat running on the PlayCanvas engine. WebGPU + Streamed SOG + Voxel Collision. [1/2]

Will Eastcott

30,993 просмотров • 2 месяцев назад