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。

The team at NVIDIA AI Developer really nailed it with ViPE!! This SLAM system generated pose, depth, point clouds, etc, in a few seconds! Now to get the output to work with GEN3C... If you are interested in running this yourself, it took about 5 minutes to get up... show more

Jonathan Stephens

13,223 subscribers

34,947 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治教育

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

THIS GUY USED CLAUDE TO BUILD A REAL TRADING BOT In just 17 minutes, he shows you how to build the same bot from scratch, refine the strategy, backtest it, and get it running. 🔖 save this before you lose it.

THIS GUY USED CLAUDE TO BUILD A REAL TRADING BOT In just 17 minutes, he shows you how to build the same bot from scratch, refine the strategy, backtest it, and get it running. 🔖 save this before you lose it.

MIKE

137,170 次观看 • 29 天前

AI provides in-depth knowledge of adrenochrome... Now you just have to ask yourself, who feeds this AI with this information and why is it allowed to talk about it in such detail? - The floodgates are open

AI provides in-depth knowledge of adrenochrome... Now you just have to ask yourself, who feeds this AI with this information and why is it allowed to talk about it in such detail? - The floodgates are open

War Correspondent

162,999 次观看 • 1 年前

this entire video is 100% AI generated and we fully automated the process it took me one message to Claude and 3 images from Nano Banana to generate a full edited video in just a few minutes - total cost was only ~$10 if you’re not using AI to get fk u rich rn you’re running out of time best time to be alive ngl

this entire video is 100% AI generated and we fully automated the process it took me one message to Claude and 3 images from Nano Banana to generate a full edited video in just a few minutes - total cost was only ~$10 if you’re not using AI to get fk u rich rn you’re running out of time best time to be alive ngl

MAX

38,413 次观看 • 6 个月前

Figured i'd give this a shot in IlluGen. Took me about 5 minutes to get to this point!

Figured i'd give this a shot in IlluGen. Took me about 5 minutes to get to this point!

Nick Seavert

18,709 次观看 • 2 个月前

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,646 次观看 • 1 年前

With the right agent harness you actually can start to make some interesting things. Case in point: This was made with Opus 5 in a few hours. It had to create the models, textures, quests, map, enemies, enemy AI, etc. And it had to load the game, play it, take screenshots and iterate.

With the right agent harness you actually can start to make some interesting things. Case in point: This was made with Opus 5 in a few hours. It had to create the models, textures, quests, map, enemies, enemy AI, etc. And it had to load the game, play it, take screenshots and iterate.

Brad Wardell

19,825 次观看 • 2 个月前

Your GPU is already there. Here's how to get paid for it. This is what running a FAR AI node looks like. We're currently in closed testing with selected partners and this is coming to you soon. Register now and be among the first to get onboarded 👉

Your GPU is already there. Here's how to get paid for it. This is what running a FAR AI node looks like. We're currently in closed testing with selected partners and this is coming to you soon. Register now and be among the first to get onboarded 👉

FAR Labs

626,873 次观看 • 5 个月前

I took a few minutes this evening to visit the cherry blossoms—they’re in peak bloom right now. If you can make it here in the next few days, you really should. It’s spectacular.

I took a few minutes this evening to visit the cherry blossoms—they’re in peak bloom right now. If you can make it here in the next few days, you really should. It’s spectacular.

Congressman Randy Fine

35,910 次观看 • 6 个月前

This store generated over $2M in sales In just 72 days…. We built it in 30 seconds with AI RT + Comment “perfume” and I’ll send you the template (must follow to get dm)

This store generated over $2M in sales In just 72 days…. We built it in 30 seconds with AI RT + Comment “perfume” and I’ll send you the template (must follow to get dm)

Henry

30,294 次观看 • 1 年前

This store generated over $1.3M in sales In just 54 days…. We built it in 30 seconds with AI RT + Comment “shower” and I’ll send you the template (must follow to get dm)

This store generated over $1.3M in sales In just 54 days…. We built it in 30 seconds with AI RT + Comment “shower” and I’ll send you the template (must follow to get dm)

Henry

25,838 次观看 • 1 年前

I generated this AI ad for CORKCICLE in 30 mins with the new AI system my team and I are building. Insane 🤯 A creator would charge $300-$500 to make this for you. Our system did it for $10 worth of credits. Comment 'ads' below if you want me to DM you early access before we release it to public

I generated this AI ad for CORKCICLE in 30 mins with the new AI system my team and I are building. Insane 🤯 A creator would charge $300-$500 to make this for you. Our system did it for $10 worth of credits. Comment 'ads' below if you want me to DM you early access before we release it to public

David Roberts

73,153 次观看 • 10 个月前

I generated this AI ad for ALT. Fragrances in 30 mins with the new AI system my team and I are building. Insane 🤯 A creator would charge $300-$500 to make this for you. Our system did it for $10 worth of credits. Comment 'Ads' below if you want me to DM you early access to the system before we release it to public (must follow for auto dm)

I generated this AI ad for ALT. Fragrances in 30 mins with the new AI system my team and I are building. Insane 🤯 A creator would charge $300-$500 to make this for you. Our system did it for $10 worth of credits. Comment 'Ads' below if you want me to DM you early access to the system before we release it to public (must follow for auto dm)

David Roberts

24,249 次观看 • 10 个月前

GPT 6 Astra is INSANE. It built the backrooms in blender and then added VHS effects etc. Took 30 minutes to make it and another 20 to export. This isn't AI generated video it's all in blender. It did the sound effects too. aprox 5 prompts.

GPT 6 Astra is INSANE. It built the backrooms in blender and then added VHS effects etc. Took 30 minutes to make it and another 20 to export. This isn't AI generated video it's all in blender. It did the sound effects too. aprox 5 prompts.

Duncan Trussell

6,382,383 次观看 • 1 个月前

Traditional SLAM: capture lidar, capture camera, fuse in post, correct drift, build map This is a Rev8 OS1 Max running SLAM down Union Street in San Francisco. The colorized point cloud is generated from a single sensor in a single pass, with color and depth captured in the same photon event

Traditional SLAM: capture lidar, capture camera, fuse in post, correct drift, build map This is a Rev8 OS1 Max running SLAM down Union Street in San Francisco. The colorized point cloud is generated from a single sensor in a single pass, with color and depth captured in the same photon event

Ouster

29,707 次观看 • 4 个月前

It took some major system rewrites but I'm starting to get the multigraph animation refactor of The Stalker 2's prototype up and running. I still have to figure out what's up with the jittering.

It took some major system rewrites but I'm starting to get the multigraph animation refactor of The Stalker 2's prototype up and running. I still have to figure out what's up with the jittering.

Max ¯\_(ツ)_/¯

16,192 次观看 • 4 个月前

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

AshutoshShrivastava

123,061 次观看 • 2 年前