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。

NLF is formulated in terms of an arbitrary keypoint estimation task, allowing to unify training data with different formats, with good pixel alignment. For SMPL output, we developed a super fast vertices-to-params fitter: And here's some more eye candy.

István Sárándi

1,178 subscribers

10,162 次观看 • 1 年前 •via X (Twitter)

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

For 3D pose some use different keypoints, others SMPL and other models. It's a mess! With Neural Localizer Fields, we can choose the output at test time! allowing to train using any. Results are real time and SOTA across the board. István Sárándi

For 3D pose some use different keypoints, others SMPL and other models. It's a mess! With Neural Localizer Fields, we can choose the output at test time! allowing to train using any. Results are real time and SOTA across the board. István Sárándi

Gerard Pons-Moll

43,531 次观看 • 2 年前

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

442,431 次观看 • 5 个月前

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

AK

305,683 次观看 • 3 年前

Another super tiny update 😅 Squeezed out these two new shots before I move to a different country. I tried to attack the character animation with simple cushions this time but added some eye candy FX for contrast. And here it is! Cheers! 🍻

Another super tiny update 😅 Squeezed out these two new shots before I move to a different country. I tried to attack the character animation with simple cushions this time but added some eye candy FX for contrast. And here it is! Cheers! 🍻

Dan Mark Lazaga

240,017 次观看 • 3 年前

Robots has a data problem, in that robotics data is rare. While human video is quite common, it’s not usually directly usable for robots for a variety of reasons, most significantly that it’s missing explicit, accurate robot actions. Instead, Jeremy Collins proposes that we predict keypoint trajectories — basically, how any given point in an object will move as a robot performs a task. This lets us use action-free human video to train robot skills. Learn more by watching Episode #37 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now.

Robots has a data problem, in that robotics data is rare. While human video is quite common, it’s not usually directly usable for robots for a variety of reasons, most significantly that it’s missing explicit, accurate robot actions. Instead, Jeremy Collins proposes that we predict keypoint trajectories — basically, how any given point in an object will move as a robot performs a task. This lets us use action-free human video to train robot skills. Learn more by watching Episode #37 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now.

RoboPapers

89,011 次观看 • 10 个月前

Code and data are now online for CameraHMR, our state-of-the-art parametric 3D human pose and shape (HPS) estimation method that will appear at hashtag#3DV2025. There are 4 key contributions that make it so accurate and robust: 1. To get accurate 3D shape and pose as well as good alignment to image features, you need to know the focal length of the camera. To solve this, we train HumanFOV to compute the field of view. 2. We introduce CameraHMR, which integrates HumanFOV into HMR2.0 to exploit the estimated focal length. 3. To get accurate pseudo ground truth (pGT) training data, we compute the focal length for images in 4DHumans dataset and modify SMPLify to take this into account. 4. But SMPLify only uses sparse 2D keypoints, which do not capture body shape. So we train a dense surface keypoint detector, DenseKP, on BEDLAM and run it on 4DHumans, resulting in improved body shape. The resulting method is CamSMPLify. We iterate training CameraHMR and running CamSMPLify on the training set initialized with CameraHMR. This results in much improved pGT for 4DHumans and a SOTA single-image HMR method.

Code and data are now online for CameraHMR, our state-of-the-art parametric 3D human pose and shape (HPS) estimation method that will appear at hashtag#3DV2025. There are 4 key contributions that make it so accurate and robust: 1. To get accurate 3D shape and pose as well as good alignment to image features, you need to know the focal length of the camera. To solve this, we train HumanFOV to compute the field of view. 2. We introduce CameraHMR, which integrates HumanFOV into HMR2.0 to exploit the estimated focal length. 3. To get accurate pseudo ground truth (pGT) training data, we compute the focal length for images in 4DHumans dataset and modify SMPLify to take this into account. 4. But SMPLify only uses sparse 2D keypoints, which do not capture body shape. So we train a dense surface keypoint detector, DenseKP, on BEDLAM and run it on 4DHumans, resulting in improved body shape. The resulting method is CamSMPLify. We iterate training CameraHMR and running CamSMPLify on the training set initialized with CameraHMR. This results in much improved pGT for 4DHumans and a SOTA single-image HMR method.

Michael Black

21,696 次观看 • 1 年前

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes even*cheaper* with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes evencheaper with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

Abhishek Gupta

13,358 次观看 • 1 年前

✨ Happy New Year from Meshcapade! ✨ We're smashing into 2025 with a massive new release. 🎉 Introducing the .SMPL format! #SMPL is a generative model for capturing and generating human behaviors, expressions, soft-tissue movement, hands & finger articulation in 3D. It is the standard for representing humans for #AI and #MachineLearning while being fully compatible with standard graphics engines. Due to its popularity, we are now making it available as a downloadable file format with all the parametric information for training your AI models. Try it out now: ➡️ Download your results as a .SMPL file for use in your AI method. ➡️ Import your own .SMPL files to view them on our online platform. 🏂 Slide into 2025 with Meshcapade & #SMPL! ✨

✨ Happy New Year from Meshcapade! ✨ We're smashing into 2025 with a massive new release. 🎉 Introducing the .SMPL format! #SMPL is a generative model for capturing and generating human behaviors, expressions, soft-tissue movement, hands & finger articulation in 3D. It is the standard for representing humans for #AI and #MachineLearning while being fully compatible with standard graphics engines. Due to its popularity, we are now making it available as a downloadable file format with all the parametric information for training your AI models. Try it out now: ➡️ Download your results as a .SMPL file for use in your AI method. ➡️ Import your own .SMPL files to view them on our online platform. 🏂 Slide into 2025 with Meshcapade & #SMPL! ✨

Meshcapade

16,363 次观看 • 1 年前

BeiDou is developed by China and is a global good. China will continue working with other nations in the spirit of openness and mutual benefit to deliver more advanced technologies for humanity.

BeiDou is developed by China and is a global good. China will continue working with other nations in the spirit of openness and mutual benefit to deliver more advanced technologies for humanity.

Mao Ning 毛宁

53,658 次观看 • 1 年前

one of my favorite aspects of this new work is that it is generative, not based on an arbitrary random number, but based on the chaos of real life. the physical sculpture is constantly pulling in news and real-time data from all over the world and the NFT is updated daily as well with this hectic collage of information overload... i believe in the future more work will be dynamic like this allowing us to reimagine real-time data in new ways based on different events happening in the world...

one of my favorite aspects of this new work is that it is generative, not based on an arbitrary random number, but based on the chaos of real life. the physical sculpture is constantly pulling in news and real-time data from all over the world and the NFT is updated daily as well with this hectic collage of information overload... i believe in the future more work will be dynamic like this allowing us to reimagine real-time data in new ways based on different events happening in the world...

beeple

155,788 次观看 • 1 年前

Mission: Show an unreleased photo of Candy. 🐮: I recently found one of my favorite photos of Candy. Q: Please show her off. 🐮: Candy is super energetic. She’s the cutest when she’s sleeping and she’s adorable when she’s awake too, but she’s so fast that you can barely even see her. Q: Is Candy a “Flame Candy” too? 🐮: Candy’s more like lightning than flames. She’s Lightning Candy, while I’m Flame Junghwan. If you want to get a good look at Candy with your own eyes, you’ll have to sneak a peek while she’s fast asleep. Lightning candy so cuteeee ㅋㅋㅋㅋ ⚡️🐶

Mission: Show an unreleased photo of Candy. 🐮: I recently found one of my favorite photos of Candy. Q: Please show her off. 🐮: Candy is super energetic. She’s the cutest when she’s sleeping and she’s adorable when she’s awake too, but she’s so fast that you can barely even see her. Q: Is Candy a “Flame Candy” too? 🐮: Candy’s more like lightning than flames. She’s Lightning Candy, while I’m Flame Junghwan. If you want to get a good look at Candy with your own eyes, you’ll have to sneak a peek while she’s fast asleep. Lightning candy so cuteeee ㅋㅋㅋㅋ ⚡️🐶

hwvnxx

22,528 次观看 • 2 个月前

If your a land holder in Texas and want to do something different than cattle Let me introduce you to Super exotic wildlife breeding is an industry that’s different, exciting, booming and fulfilling. Huge tax incentives and consistent ROI. Plus the feel good of conservation for some incredibly beautiful animals that the world simply needs more of!

If your a land holder in Texas and want to do something different than cattle Let me introduce you to Super exotic wildlife breeding is an industry that’s different, exciting, booming and fulfilling. Huge tax incentives and consistent ROI. Plus the feel good of conservation for some incredibly beautiful animals that the world simply needs more of!

Luke McCown

31,563 次观看 • 1 个月前

Model progress is no longer constrained by architecture, but by access to high-quality, human-generated data. Scraped internet data is finite, low-signal and increasingly synthetic. Kled AI pays real people to upload authentic, real world content task by task in their mobile app. We are super excited to back Avi Patel and Kled AI as they build a massive data marketplace. If you are in need of a great data partner, reach out! More from us here (we were not investors when we filmed):

Model progress is no longer constrained by architecture, but by access to high-quality, human-generated data. Scraped internet data is finite, low-signal and increasingly synthetic. Kled AI pays real people to upload authentic, real world content task by task in their mobile app. We are super excited to back Avi Patel and Kled AI as they build a massive data marketplace. If you are in need of a great data partner, reach out! More from us here (we were not investors when we filmed):

Nichole Wischoff

37,136 次观看 • 5 个月前

What more do we need to see before we acknowledge this "free Palestine" movement is nothing more than a domestic terror organization? We are in a FIGHT for the future of Western civilization and we need to come to grips with it — and fast.

What more do we need to see before we acknowledge this "free Palestine" movement is nothing more than a domestic terror organization? We are in a FIGHT for the future of Western civilization and we need to come to grips with it — and fast.

Scott Jennings

668,212 次观看 • 1 年前

$VELO Q&A Audio: - Defense contracts have been a big driver - Secured over 70 different space programs this year - Expected to close only 10% of the deals but closing over 40%; closing really fast - We are in contact for SpaceX (for Raptor 4); they are increasing their fleet and also sending us parts to print. We are on good terms with SpaceX - Anduril is a customer of Velo. We are already working with many programs together and they are increasing their parts. We are also combining our forces to bid for other programs - We are in talks with SpaceX for them to buy more machines. Can't disclose more details but most likely they will. - We are already seeing the massive increase in drone demand in our allocation with Anduril and SpaceX together. Velo3D is the choice for a lot of these programs due to the US manufacturing large metal size.

$VELO Q&A Audio: - Defense contracts have been a big driver - Secured over 70 different space programs this year - Expected to close only 10% of the deals but closing over 40%; closing really fast - We are in contact for SpaceX (for Raptor 4); they are increasing their fleet and also sending us parts to print. We are on good terms with SpaceX - Anduril is a customer of Velo. We are already working with many programs together and they are increasing their parts. We are also combining our forces to bid for other programs - We are in talks with SpaceX for them to buy more machines. Can't disclose more details but most likely they will. - We are already seeing the massive increase in drone demand in our allocation with Anduril and SpaceX together. Velo3D is the choice for a lot of these programs due to the US manufacturing large metal size.

Tut C🅰️pital

54,170 次观看 • 9 个月前

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

a16z

76,834 次观看 • 1 个月前

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.

elvis

141,023 次观看 • 1 年前

Ukraine is participating in all formats of engagement with our partners for more security and shared strength. We continue to work with countries that are currently under attack by the Iranian regime. New arrangements have been reached, and Ukraine will have an even greater presence in the new security formats. This will certainly strengthen Ukraine's export potential and defense capabilities.

Ukraine is participating in all formats of engagement with our partners for more security and shared strength. We continue to work with countries that are currently under attack by the Iranian regime. New arrangements have been reached, and Ukraine will have an even greater presence in the new security formats. This will certainly strengthen Ukraine's export potential and defense capabilities.

Volodymyr Zelenskyy / Володимир Зеленський

232,672 次观看 • 5 个月前