正在加载视频...

视频加载失败

返回首页

This new AI tool is interesting! ReconX can create a 3D scene using just two images from different angles. Imagine if we could train our character with only 2 images instead of 10?

EHuanglu's profile picture

el.cine

129,491 subscribers

69,436 次观看 • 1 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

el.cine 的头像
el.cine1 年前

Paper:

TomLikesRobots🤖 的头像
TomLikesRobots🤖1 年前

Interesting that it's not Google but they utilise Imagen and Phenaki. Unfortunately, it might also mean we won't get to play with it. This looks like a really interesting tool.

Hungry Donk-E 的头像
Hungry Donk-E1 年前

🥕Wow! This is awesome! I recently tried something similar here using i2v

MayorkingAI 的头像
MayorkingAI1 年前

very interesting!

el.cine 的头像
el.cine1 年前

👍👍

Ivan P. 的头像
Ivan P.1 年前

@SmagaAlex, we should explain how @Openmagic_ai functions in a similar manner.

Michael Ten 🌨🎶🫐🍀 的头像
Michael Ten 🌨🎶🫐🍀1 年前

That's pretty cool. Machine learning sure is advancing quickly

el.cine 的头像
el.cine1 年前

It’s super quick mate

andwhynut 的头像
andwhynut1 年前

pinta fresco este reconX, Thx for sharing!!! have u seen the new vidu?

Teodora P L 的头像
Teodora P L1 年前

Ooo wow this is going to be killer for Teal Estate

相关视频

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.
0:46

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.

Hashem Al-Ghaili

29,185 次观看 • 1 年前

The fun part of using Kling 3.0 Omni Kling AI is that you only need one character sheet, so you can focus on writing the scene instead of animating images one by one. The base character was generated with Grok Imagine, and I turned it into a character sheet using Nano Banana Pro via Freepik (now Magnific).
1:05

The fun part of using Kling 3.0 Omni Kling AI is that you only need one character sheet, so you can focus on writing the scene instead of animating images one by one. The base character was generated with Grok Imagine, and I turned it into a character sheet using Nano Banana Pro via Freepik (now Magnific).

DAN · MXVDXN

13,278 次观看 • 4 个月前

Generative AI is making big leaps every passing day. Found ChatGPT interesting, check out this new AI model from CMU that can bring your ideas to life. AI that can create brilliant 3D renders from 2D images in a matter of seconds 🤯
0:30

Generative AI is making big leaps every passing day. Found ChatGPT interesting, check out this new AI model from CMU that can bring your ideas to life. AI that can create brilliant 3D renders from 2D images in a matter of seconds 🤯

Shubham Saboo

100,800 次观看 • 3 年前

welcome to Stage. this experimental tool lets you create entire 3D environments with AI from images or text. try it now!
0:30

welcome to Stage. this experimental tool lets you create entire 3D environments with AI from images or text. try it now!

Krea

253,935 次观看 • 1 年前

Found very cool ai tool that can create progress video like this for all your ai images.
0:49

Found very cool ai tool that can create progress video like this for all your ai images.

Ilya | SuperRare

1,431,154 次观看 • 2 年前

If they are doing this with AI imagine what else they could be doing. AI generating images of children should be illegal!
0:28

If they are doing this with AI imagine what else they could be doing. AI generating images of children should be illegal!

Michael

86,490 次观看 • 3 个月前

Google Labs just dropped Whisk, a fun new AI image tool. You can remix your ideas into digital magic. You can prompt or input image to create unique images from subject, scene, and style. Quick example and how to try:
0:31

Google Labs just dropped Whisk, a fun new AI image tool. You can remix your ideas into digital magic. You can prompt or input image to create unique images from subject, scene, and style. Quick example and how to try:

Min Choi

117,648 次观看 • 1 年前

This is the easiest way to create splats. You can create from AI images. Pretty amazing. Easy to install using Created by franzipol 👍
0:25

This is the easiest way to create splats. You can create from AI images. Pretty amazing. Easy to install using Created by franzipol 👍

alexcovo.eth

67,484 次观看 • 6 个月前

Take your creativity to new heights! Now you can create a video from just three images and an AI prompt, all using Veo 3.1 in Google Vids. →
0:35

Take your creativity to new heights! Now you can create a video from just three images and an AI prompt, all using Veo 3.1 in Google Vids. →

Google Workspace

25,949 次观看 • 7 个月前

I searched through over 100+ new AI tools this week. The top 10 most interesting ones that you've never heard about: 1. Genmo Create and edit videos or images from text using GPT-4.
0:59

I searched through over 100+ new AI tools this week. The top 10 most interesting ones that you've never heard about: 1. Genmo Create and edit videos or images from text using GPT-4.

Rowan Cheung

1,106,704 次观看 • 3 年前

Woah, look at this. Google, $GOOGL, has just showcased Genie 2, a model that can create 3D playable worlds from 2D images, without a game engine:
0:34

Woah, look at this. Google, $GOOGL, has just showcased Genie 2, a model that can create 3D playable worlds from 2D images, without a game engine:

unusual_whales

429,138 次观看 • 1 年前

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito
0:38

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,698 次观看 • 1 年前

3D Gaussian is great, but how can you interact with it 🌹👋? Introducing #PhysDreamer: Create your own realistic interactive 3D assets from only static images! Discover how we do this below👇 🧵1/: Website:
0:27

3D Gaussian is great, but how can you interact with it 🌹👋? Introducing #PhysDreamer: Create your own realistic interactive 3D assets from only static images! Discover how we do this below👇 🧵1/: Website:

Tianyuan Zhang

60,840 次观看 • 2 年前

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.
0:32

3D AI is advancing quicker than we ever thought possible. Right now, we can use it to create individual 3D assets, but soon, building entire virtual worlds with just a text prompt could become a reality. This is from Meta 3D AI team.

el.cine

42,166 次观看 • 1 年前

2/ Generate images with extreme precision Forget generic AI art Qwen can create highly detailed, instruction-following images that rival top-tier AI generators. The level of accuracy is insane.
0:21

2/ Generate images with extreme precision Forget generic AI art Qwen can create highly detailed, instruction-following images that rival top-tier AI generators. The level of accuracy is insane.

Ihtesham Haider

187,817 次观看 • 1 年前

Instant Video-to-3D with DUST3R Dust3r generates a whole 3D scene from just a couple of images. What if it could: 1. Accept a VIDEO 2. Extract the video frames 3. Turn them into 3D? So added a Gradio Video Component. Here's me generating 3D from a video cc: NAVER LABS Europe
1:13

Instant Video-to-3D with DUST3R Dust3r generates a whole 3D scene from just a couple of images. What if it could: 1. Accept a VIDEO 2. Extract the video frames 3. Turn them into 3D? So added a Gradio Video Component. Here's me generating 3D from a video cc: NAVER LABS Europe

cocktail peanut

41,029 次观看 • 2 年前