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.

Many works model 3D virtual humans, but how can we create realistic dense crowds? At SIGGRAPH Asia 2024, we will show that solving human-human interactions is key to modeling realistic crowds. project: 🧵1/4

Dan Casas

1,841 subscribers

22,771 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

9 Comments

Dan Casas1 year ago

By approximating each individual with a parametric set of 3D volumetric proxies, we resolve human-human interactions while maintaining the overall motion of the crowd. Previous methods for dense crowds modeled humans as 2D disks instead of 3D articulated volumes. 2/4

Dan Casas1 year ago

We validate our approach through an extensive user study, using videos of crowds at 5 different density levels, rendered from 4 viewpoints. Our results demonstrate that resolving collisions is crucial for improving the realism of dense 3D crowds.

Dan Casas1 year ago

Joint work from @etsii_urjc (Madrid, Spain) and @Inria (Rennes, France), as part of the @CrowdDNA_H2020 project. It will be presented in Tokyo for SIGGRAPH Asia 2024. Check our project website for more details.

German Barquero1 year ago

Great work, Dan!! Congrats to the team!!

Silvia Sellán1 year ago

Really cool work, Dan! Can’t wait to see it presented in Tokyo :)

Michael Black1 year ago

Congratulations! I really like it.

Dan Casas1 year ago

Thank you, Michael! 🙏

Xiaohan Zhang1 year ago

Congrats on the fantastic work! Just wondering if there will be a code release down the timeline?

Dan Casas1 year ago

We plan to release the code, yes. Notice, however, that most of the physics stuff is borrowed from FLSH, which is already available here and

Related Videos

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference.

Check out Christian Diller's CG-HOI :) We generate realistic 3D human-object interactions, from object geometry and text description. A key ingredient is explicit modeling of contact, during training and as guidance during inference.

Angela Dai

20,514 views • 2 years ago

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:

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

60,873 views • 2 years ago

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n

Chuang Gan

90,349 views • 1 year ago

Existing 3D human manipulation datasets are valuable, but are limited in scale and diversity. At #CVPR2025, we will introduce GigaHands👐 which, to our knowledge, is the most extensive 3D bimanual manipulation, interaction, and gesture dataset.🧵👇(1/9)

Existing 3D human manipulation datasets are valuable, but are limited in scale and diversity. At #CVPR2025, we will introduce GigaHands👐 which, to our knowledge, is the most extensive 3D bimanual manipulation, interaction, and gesture dataset.🧵👇(1/9)

Srinath Sridhar

13,581 views • 1 year ago

Multi-modal #LLMs understand a lot about humans. But do they understand our 3D pose? We train #PoseGPT to estimate, generate, and reason about 3D human pose (#SMPL) in images and text. This is the first true foundation model for understanding 3D humans.

Multi-modal #LLMs understand a lot about humans. But do they understand our 3D pose? We train #PoseGPT to estimate, generate, and reason about 3D human pose (#SMPL) in images and text. This is the first true foundation model for understanding 3D humans.

Michael Black

81,430 views • 2 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

14,610 views • 1 year ago

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

Matthias Niessner

69,697 views • 3 years ago

How far can a very simple eye go in solving vision tasks? Like a 1-pixel camera? Humans have one of the greatest eyes in nature, while many animals have significantly simpler eyes and visual systems yet show complex perceptual behavior. In an interesting project, we find that many computer vision tasks can be solved without a typical camera and with such simple 1-pixel sensors (photoreceptors). We also find that proper design (e.g., where to place the photoreceptors strategically) makes a big difference, so we developed a computational design method to find them. 🌐 👁️[Solving Vision Tasks with Simple Photoreceptors Instead of Cameras] 🧵1/n

How far can a very simple eye go in solving vision tasks? Like a 1-pixel camera? Humans have one of the greatest eyes in nature, while many animals have significantly simpler eyes and visual systems yet show complex perceptual behavior. In an interesting project, we find that many computer vision tasks can be solved without a typical camera and with such simple 1-pixel sensors (photoreceptors). We also find that proper design (e.g., where to place the photoreceptors strategically) makes a big difference, so we developed a computational design method to find them. 🌐 👁️[Solving Vision Tasks with Simple Photoreceptors Instead of Cameras] 🧵1/n

Amir Zamir

75,892 views • 2 years ago

📁 Yann LeCun says that AGI does not exist and is a poorly defined concept built around an idealized view of human intelligence. He argues that humans are highly specialized, good at navigating the physical and social world, but weak at many other tasks. We seem general only because we can imagine the problems we are good at. For LeCun, AGI mistakes human limits for universal laws of intelligence.

📁 Yann LeCun says that AGI does not exist and is a poorly defined concept built around an idealized view of human intelligence. He argues that humans are highly specialized, good at navigating the physical and social world, but weak at many other tasks. We seem general only because we can imagine the problems we are good at. For LeCun, AGI mistakes human limits for universal laws of intelligence.

Jon Hernandez

28,104 views • 8 months ago

f*ck it. I'm LEAKING my entire Seedance 2.0 AI UGC System i cracked the formula for generating seedance 2.0 videos that look hyper realistic this has been gatekept for a while, but i'm finally sharing my FULL system with you.. here's what you're getting: - my prompting method for realistic voices (works every time) - my realistic human movements & breathing claude skill (this is key for realistic videos) - my exact method on how to make infinite length videos that maintain consistency - how to get AI tools for dirt cheap (90% off) RT + reply 'UGC' and i'll send you the step-by-step system (must follow so i can dm)

f*ck it. I'm LEAKING my entire Seedance 2.0 AI UGC System i cracked the formula for generating seedance 2.0 videos that look hyper realistic this has been gatekept for a while, but i'm finally sharing my FULL system with you.. here's what you're getting: - my prompting method for realistic voices (works every time) - my realistic human movements & breathing claude skill (this is key for realistic videos) - my exact method on how to make infinite length videos that maintain consistency - how to get AI tools for dirt cheap (90% off) RT + reply 'UGC' and i'll send you the step-by-step system (must follow so i can dm)

Miko

44,994 views • 23 days ago

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,793 views • 1 year ago

Today, we’re excited to launch Attention Labs. For almost 400,000 years, humanity has progressed through a simple but powerful cycle: we learn, we build, and we pass knowledge forward. Every major leap in civilization, from fire to medicine to computing, has expanded what humans are capable of achieving. We believe AI is the next great tool in that journey. While much of the world is focused on how AI can replace human work, we are focused on a different question: How can AI amplify human potential? At Attention Labs, we are building AI to discover brain-enhancing therapeutics, solve neurocognitive diseases, and accelerate the discovery of medicines for the human mind. We believe the greatest opportunity for AI is not creating a world with fewer humans in the loop, but a world where every human can think more clearly, learn faster, create more boldly, and live more fully. The biggest source of alpha in the age of AI will not come from replacing people. It will come from empowering them. Our mission is simple: Make humans the most intelligent entity on Earth. The future belongs to those who amplify human intelligence, not those who seek to replace it. We're just getting started. Attention Labs

Today, we’re excited to launch Attention Labs. For almost 400,000 years, humanity has progressed through a simple but powerful cycle: we learn, we build, and we pass knowledge forward. Every major leap in civilization, from fire to medicine to computing, has expanded what humans are capable of achieving. We believe AI is the next great tool in that journey. While much of the world is focused on how AI can replace human work, we are focused on a different question: How can AI amplify human potential? At Attention Labs, we are building AI to discover brain-enhancing therapeutics, solve neurocognitive diseases, and accelerate the discovery of medicines for the human mind. We believe the greatest opportunity for AI is not creating a world with fewer humans in the loop, but a world where every human can think more clearly, learn faster, create more boldly, and live more fully. The biggest source of alpha in the age of AI will not come from replacing people. It will come from empowering them. Our mission is simple: Make humans the most intelligent entity on Earth. The future belongs to those who amplify human intelligence, not those who seek to replace it. We're just getting started. Attention Labs

Temi

37,046 views • 2 months ago

🔥 Introducing MVLift: Generate realistic 3D motion without any 3D training data - just using 2D poses from monocular videos! Applicable to human motion, human-object interaction & animal motion. Joint work w/ Jiajun Wu & Karen 💡 How? We reformulate 3D motion estimation as generating consistent multi-view 2D pose sequences. Our framework uses 2D motion diffusion to progressively establish multi-view consistency, requiring only single-view 2D pose sequences for training. Project: Video with demonstration: Paper:

🔥 Introducing MVLift: Generate realistic 3D motion without any 3D training data - just using 2D poses from monocular videos! Applicable to human motion, human-object interaction & animal motion. Joint work w/ Jiajun Wu & Karen 💡 How? We reformulate 3D motion estimation as generating consistent multi-view 2D pose sequences. Our framework uses 2D motion diffusion to progressively establish multi-view consistency, requiring only single-view 2D pose sequences for training. Project: Video with demonstration: Paper:

Jiaman Li

15,886 views • 1 year ago

Elon Musk: We are approaching the Singularity, a future where work is optional, and if you can think of it, you can have it But human consumption has limits. Eventually, AI will saturate everything humans could want At that point, machines start serving themselves once humans need nothing more

Elon Musk: We are approaching the Singularity, a future where work is optional, and if you can think of it, you can have it But human consumption has limits. Eventually, AI will saturate everything humans could want At that point, machines start serving themselves once humans need nothing more

Haider.

506,761 views • 8 months ago

[SIGGRAPH '25] EVA: Expressive Virtual Avatars from Multi-view Videos Contributions: 1. We introduce EVA, a novel method enabling full-body control with real-time, photo-realistic renderings, robustly handling loose clothing dynamics and various facial expressions. 2. We develop an expressive deformable template that generates a deformable human template mesh and employs a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.

[SIGGRAPH '25] EVA: Expressive Virtual Avatars from Multi-view Videos Contributions: 1. We introduce EVA, a novel method enabling full-body control with real-time, photo-realistic renderings, robustly handling loose clothing dynamics and various facial expressions. 2. We develop an expressive deformable template that generates a deformable human template mesh and employs a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.

MrNeRF

18,407 views • 1 year ago

Can we treat brain disorders by restoring neural connections? For centuries, neuroscientists could only guess. But connectomics—a method seeking to create a 3D model of every neural connection in the brain—is moving closer to providing answers. @E11Bio is at the forefront...🧵

Can we treat brain disorders by restoring neural connections? For centuries, neuroscientists could only guess. But connectomics—a method seeking to create a 3D model of every neural connection in the brain—is moving closer to providing answers. @E11Bio is at the forefront...🧵

Asimov Press

32,954 views • 1 year ago

AI that had human-level intelligence would actually be way above human level in capability. Obviously, if we trained a human-level AI, we could just run way more instances of it in parallel. This is a huge advantage. But it's not the only one. Right now, LLMs are much less sample-efficient than humans, but they can process each individual piece of data much more quickly. A model that was a human-level learner would be able to gain the equivalent of thousands of years of education. AIs can also be way more task-oriented than humans. Even a really well-motivated human worker can only operate with ‘human-level’ effort for relatively short spans of time. AGI could do it continuously.

AI that had human-level intelligence would actually be way above human level in capability. Obviously, if we trained a human-level AI, we could just run way more instances of it in parallel. This is a huge advantage. But it's not the only one. Right now, LLMs are much less sample-efficient than humans, but they can process each individual piece of data much more quickly. A model that was a human-level learner would be able to gain the equivalent of thousands of years of education. AIs can also be way more task-oriented than humans. Even a really well-motivated human worker can only operate with ‘human-level’ effort for relatively short spans of time. AGI could do it continuously.

Dwarkesh Patel

31,861 views • 3 months ago

📁 Yann LeCun says that scaling models will not get us to human intelligence. He explains that the industry remains obsessed with making LLMs bigger, but that this path is fundamentally broken. It does not matter how many parameters we add or how many clusters we build, because the models only imitate language patterns. Human intelligence does not emerge from size, it emerges from understanding the world.

📁 Yann LeCun says that scaling models will not get us to human intelligence. He explains that the industry remains obsessed with making LLMs bigger, but that this path is fundamentally broken. It does not matter how many parameters we add or how many clusters we build, because the models only imitate language patterns. Human intelligence does not emerge from size, it emerges from understanding the world.

Jon Hernandez

157,988 views • 8 months ago

i should never be sharing this but f*ck it Gemini Omni + GPT Images 2 + tiktok is THE best combo for AI videos i cracked the formula for generating videos that look hyper realistic & make your audience feel like "holy shit this person gets me" i'm finally sharing my FULL system with you.. here's what you're getting: - my prompting method for realistic voices (works every time) - my realistic human movements & breathing trick (this is key for realistic videos) - my exact method on how to make infinite length videos that maintain consistency - how to get AI tools for dirt cheap (90% off) RT + reply 'OMNI' and i'll send you the step-by-step system (must be following so i can dm)

i should never be sharing this but f*ck it Gemini Omni + GPT Images 2 + tiktok is THE best combo for AI videos i cracked the formula for generating videos that look hyper realistic & make your audience feel like "holy shit this person gets me" i'm finally sharing my FULL system with you.. here's what you're getting: - my prompting method for realistic voices (works every time) - my realistic human movements & breathing trick (this is key for realistic videos) - my exact method on how to make infinite length videos that maintain consistency - how to get AI tools for dirt cheap (90% off) RT + reply 'OMNI' and i'll send you the step-by-step system (must be following so i can dm)

Miko

146,044 views • 1 month ago