正在加载视频...

视频加载失败

We can replay the HO-Cap data in #IsaacSim No physics enabled. It is setting the poses of hands and objects according to our annotations

41,550 次观看 • 1 年前 •via X (Twitter)

5 条评论

Chen Tessler 的头像
Chen Tessler1 年前

Nice!

RedDeer.Games 的头像
RedDeer.Games1 年前

We can't spill the beans about the release date of Maki: Paw of Fury, but make no mistake, things are happening! 🫘😎 We remind you that the game is coming to #NintendoSwitch and #PC #Steam and you can play the demo on PC, here ⤵️ >>> Have a great day!

Chris Matthieu 的头像
Chris Matthieu1 年前

Awesome!

Igor Kotenkov 的头像
Igor Kotenkov1 年前

mind sharing the code? (haven't seen it in the main hocap repo, maybe I've missed it)

Yu Xiang 的头像
Yu Xiang1 年前

It is still an ongoing project. We will share the code later

相关视频

Pioneers, the Revolution Is in Our Hands! 🌏 We are living in a historic moment! Pi Network is not just another cryptocurrency – it is a global movement that can forever transform the world’s financial system. But for this to happen, we must act with intelligence, unity, and determination. We are millions of Pioneers across the planet, connected by a single ideal: building a decentralized, fair, and accessible future for all. No government, bank, or financial elite can dictate the value of Pi. We are the force driving this revolution! The True Value of Pi Is in Our Hands! The GCV of $314,159 is not just a number – it is a symbol of our vision, our confidence, and our mission. Pi is worth what we believe and make happen. If we want to see Pi shine, we must act now: Say NO to exchanges that try to manipulate Pi’s value! Withdraw and protect your coins. Refuse to sell your Pi for unfair prices! We determine its value. Use Pi in real transactions! The more we use it, the stronger it becomes. Spread the word, encourage others, make history! The more people believe, the more powerful it gets. Create scarcity! The harder it is to obtain Pi, the more valuable it will be. The World Is Watching – Let’s Show Them Our Strength! The early days of Bitcoin were filled with uncertainty. Many doubted it. Today, it is a global phenomenon! Now, we stand before an even greater moment: the birth of a cryptocurrency that is truly accessible to all. But Pi’s future will not be written by speculators. It will be written by US! The decision is in our hands. We can allow our dream to be manipulated, or we can change history and make Pi a global powerhouse! If every Pioneer acts with faith, strategy, and commitment, the GCV of $314,159 will not be a wish – it will be an undeniable reality! Together, we are unstoppable! The future is now! I am Sérgio Cruz, the Global GCV Ambassador from Portugal 🇵🇹

Doris Yin 东方紫莲🪷

17,699 次观看 • 1 年前

Physics-based Motion Retargeting from Sparse Inputs paper page: Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time. We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.

AK

106,519 次观看 • 3 年前