Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

"A Generative Motion Rig for Artist Driven Motion Authoring" from Disney Research Zurich and ETH Zurich So cool! Full video: Paper:

Chris Offner

4,781 subscribers

38,126 views • 3 months ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

9 Comments

Yun3 months ago

what a beautiful work 🥸

Edmond3 months ago

so where's the plugin?

Bounty Hunter3 months ago

Amazing work ! Is it open source ?

SNDAYS3 months ago

@sidefx

Stüssy Senik3 months ago

Wow, this is exciting!! Very organic motion.

AmyNote3 months ago

Framing this as a rig instead of a text-to-motion box is the actual unlock — the bottleneck was never generation quality, it was giving artists a handle they can iterate against like any other slider.

Dungeon Fox3 months ago

oh hey this is pretty much the method I use but I have a sparse to dense processor in-between. really realizing the faults of using AI and Hardware that steals data...meh will be nice to eventually use technology to track down every instance.

AI Mastery Guide3 months ago

Sampling different motions like that gives artists so much more control

StudioGaltMocap3 months ago

Would to see if this could be used to transition with sign language animations. Most inbetweening systems are still quite robotic.

Related Videos

badminton robot from ETH Zurich

badminton robot from ETH Zurich

pfung

229,466 views • 1 year ago

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

AK

160,787 views • 3 years ago

$Example-based Motion Synthesis via Generative Motion Matching paper page: present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual artifacts, and tend to fail on large and complex skeletons, GenMM inherits the training-free nature and the superior quality of the well-known Motion Matching method. GenMM can synthesize a high-quality motion within a fraction of a second, even with highly complex and large skeletal structures. At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches. In addition to diverse motion generation, we show the versatility of our generative framework by extending it to a number of scenarios that are not possible with motion matching alone, including motion completion, key frame-guided generation, infinite looping, and motion reassembly.$

Example-based Motion Synthesis via Generative Motion Matching paper page: present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual artifacts, and tend to fail on large and complex skeletons, GenMM inherits the training-free nature and the superior quality of the well-known Motion Matching method. GenMM can synthesize a high-quality motion within a fraction of a second, even with highly complex and large skeletal structures. At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches. In addition to diverse motion generation, we show the versatility of our generative framework by extending it to a number of scenarios that are not possible with motion matching alone, including motion completion, key frame-guided generation, infinite looping, and motion reassembly.

AK

93,773 views • 3 years ago

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,728 views • 1 year ago

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

A new paper by Disney Research introduces a 2-stage technique for motion tracking in physics-based character animation, using a pretrained latent space and RL to control diverse and unseen motions on both virtual and real-world humanoid robots. Paper:

The Humanoid Hub

20,117 views • 2 years ago

Fully Funded Master's at ETH Zurich Switzerland 🇨🇭

Fully Funded Master's at ETH Zurich Switzerland 🇨🇭

Ghost 👨🏽‍💻🇨🇦

35,346 views • 6 months ago

Transformer robot is now opening doors for you! ETH Zürich @swiss_mile D-MAVT, ETH Zurich Full video: Authors: Clemens Schwarke, Victor Klemm, Matthijs van der Boon, Marko Bjelonic, and Marco Hutter #robotics #ai #reinforcementlearning #ethzurich

Transformer robot is now opening doors for you! ETH Zürich @swiss_mile D-MAVT, ETH Zurich Full video: Authors: Clemens Schwarke, Victor Klemm, Matthijs van der Boon, Marko Bjelonic, and Marco Hutter #robotics #ai #reinforcementlearning #ethzurich

Robotic Systems Lab

105,598 views • 3 years ago

$Check out the online demo for #OpenNeRF ✨ ➡️ 🚀 📄Paper: 👩‍💻Code: 📽️ Project: \w Federico Tombari Marc Pollefeys Michael Niemeyer et al. ICLR ETH Zurich ETH AI Center Google AI$

Check out the online demo for #OpenNeRF ✨ ➡️ 🚀 📄Paper: 👩‍💻Code: 📽️ Project: \w Federico Tombari Marc Pollefeys Michael Niemeyer et al. ICLR ETH Zurich ETH AI Center Google AI

Francis Engelmann

23,670 views • 2 years ago

POV: We make a cool Motion video for your company

POV: We make a cool Motion video for your company

Aizal Khan

28,557 views • 1 month ago

From live video to 3D avatar in seconds. This #SIGGRAPH2025 paper from Adobe Research reconstructs a realistic head avatar on the fly, with no pre-cached data, and adapts seamlessly to facial motion for VR, animation, and online communication. 🔗

Adobe Research

29,286 views • 1 year ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 views • 2 years ago

What is missing to bring real-time motion research into AAA games and real-world robotics? We present MotionBricks, a step toward bridging this gap with two key components: - a single generative latent motion backbone covering 350,000+ motion skills, running at 15,000 FPS with 2 ms latency and substantially improved quality and reliability. - a unified smart primitive interface for locomotion, object / scene interaction, with fine-grained control over generated behaviors. Webpage: Code: Paper: (ACM TOG / SIGGRAPH 2026)

What is missing to bring real-time motion research into AAA games and real-world robotics? We present MotionBricks, a step toward bridging this gap with two key components: - a single generative latent motion backbone covering 350,000+ motion skills, running at 15,000 FPS with 2 ms latency and substantially improved quality and reliability. - a unified smart primitive interface for locomotion, object / scene interaction, with fine-grained control over generated behaviors. Webpage: Code: Paper: (ACM TOG / SIGGRAPH 2026)

tingwu.wang

154,801 views • 6 months ago

Generative video is dope but AI motion capture is just as cool. Pretty much James Cameron ish in your living room — and that too with just a 2D camera

Generative video is dope but AI motion capture is just as cool. Pretty much James Cameron ish in your living room — and that too with just a 2D camera

Bilawal Sidhu

89,178 views • 2 years ago

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,403 views • 3 years ago

Happy new week. A fountain and a part of the Swiss alps at the end. Switzerland - Zurich - Lake Zurich

Happy new week. A fountain and a part of the Swiss alps at the end. Switzerland - Zurich - Lake Zurich

Nicole Zierer

51,572 views • 1 year ago

Forza Motorsport Fujimi Kaido PSR Full Motion Sim Rig

Forza Motorsport Fujimi Kaido PSR Full Motion Sim Rig

Virtual Motorsports Studio

30,245 views • 1 year ago