Loading video...

Video Failed to Load

Go Home

Introducing Akari: a frontier learned rendering model for robotics simulation. Akari generates photorealistic rendering for any physics engine to close the sim-to-real gap. Trained in-house, it is the fastest and highest-fidelity learned renderer in any sim platform: 0.046 LPIPS at 0.5s/frame, consistent across 1K+ frames.

MidcenturyAI's profile picture

Midcentury

2,606 subscribers

22,131 views • 5 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

just made it possible to evaluate generalist robotics models like Octo at 60-100x real world evaluation speeds via gpu simulation and rendering (~10x faster than original cpu sim code). All videos below are from our open source ManiSkill GPU sim!
0:12

just made it possible to evaluate generalist robotics models like Octo at 60-100x real world evaluation speeds via gpu simulation and rendering (~10x faster than original cpu sim code). All videos below are from our open source ManiSkill GPU sim!

Stone Tao

13,456 views • 2 years ago

Bringing new meaning to the word NeRD at #CoRL2025. 🤓 Neural Robot Dynamics (NeRD) bridges the sim-to-real gap with a hybrid of neural modeling and analytical simulation, unlocking zero-shot transfer and continuous learning loops for optimal robotics training. Read more & try it in Newton 🤖
0:10

Bringing new meaning to the word NeRD at #CoRL2025. 🤓 Neural Robot Dynamics (NeRD) bridges the sim-to-real gap with a hybrid of neural modeling and analytical simulation, unlocking zero-shot transfer and continuous learning loops for optimal robotics training. Read more & try it in Newton 🤖

NVIDIA Robotics

17,556 views • 1 year ago

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.
0:14

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.

Robora

23,540 views • 1 year ago

I've had a chance to try an upcoming photorealistic Lens Sim plugin for Blender by Håvard Dalen , and in fact I prepared an extensive video review of it that will be out tomorrow. In brief: once Lens Sim is out, photoreal #3d rendering will never be the same. #b3d 🧵 1/?
0:12

I've had a chance to try an upcoming photorealistic Lens Sim plugin for Blender by Håvard Dalen , and in fact I prepared an extensive video review of it that will be out tomorrow. In brief: once Lens Sim is out, photoreal #3d rendering will never be the same. #b3d 🧵 1/?

Gleb Alexandrov

15,167 views • 1 year ago

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall. DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality. Learn More →
0:19

Announcing NVIDIA DLSS 5, an AI-powered breakthrough in visual fidelity for games, coming this fall. DLSS 5 infuses pixels with photorealistic lighting and materials, bridging the gap between rendering and reality. Learn More →

Rock Solid

13,360 views • 7 months ago

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.
0:18

The concept of creating an exact digital replica of the physical world has always fascinated me: environments that look and behave exactly like our everyday reality, precisely captured in the digital domain. This is the essence of 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬, simulated realities indistinguishable from our own. Generating these models is the core mission behind what we are building at SpAItial AI. True World Models must capture both photorealistic appearance and underlying physics, spatially-consistent across the environment. For static scenes, current models already deliver impressive results, unlocking downstream applications from gaming to 3D design. However, the true frontier lies in modeling dynamics, which will enable the training of AI agents whose learned behaviors can bridge the sim-to-real gap, thus unlocking countless real-world applications.

Matthias Niessner

21,734 views • 8 months ago

How does high-fidelity tactile simulation help robots nail the last millimeter? We’re releasing VT-Refine, accepted to CoRL: a real-to-sim-to-real visuo-tactile policy using a GPU-parallel tactile sim for our piezoresistive skin FlexiTac. Then fine-tuning a diffusion policy with large-scale RL in simulation. Website: #CoRL2025 #RobotLearning #Sim2Real
0:17

How does high-fidelity tactile simulation help robots nail the last millimeter? We’re releasing VT-Refine, accepted to CoRL: a real-to-sim-to-real visuo-tactile policy using a GPU-parallel tactile sim for our piezoresistive skin FlexiTac. Then fine-tuning a diffusion policy with large-scale RL in simulation. Website: #CoRL2025 #RobotLearning #Sim2Real

Binghao Huang

46,982 views • 1 year ago

an important optim for any isometric RTS: split the map into sectors, and do frustum culling. I know that Unity already has great culling, but it feel wrong to only rely on Unity for it, what if we want to have huge maps? Of course, logic and rendering has to be completely decoupled, because entities in invisible sectors still need to "think". And of course, I broke the minimap because all sectors must be visible in it at all times. But it's fixable by manipulating visibility though rendering layers instead of mesh renderer state.
0:14

an important optim for any isometric RTS: split the map into sectors, and do frustum culling. I know that Unity already has great culling, but it feel wrong to only rely on Unity for it, what if we want to have huge maps? Of course, logic and rendering has to be completely decoupled, because entities in invisible sectors still need to "think". And of course, I broke the minimap because all sectors must be visible in it at all times. But it's fixable by manipulating visibility though rendering layers instead of mesh renderer state.

Amine Rehioui

62,604 views • 11 months ago

Meet Cleo, created and rendered by #gnomonworkshopinstructor Şefki Ibrahim, developed in Maya and Arnold, and prepped for real-time and rendering in UE5. Learn Sefki's photorealistic character workflows at
0:19

Meet Cleo, created and rendered by #gnomonworkshopinstructor Şefki Ibrahim, developed in Maya and Arnold, and prepped for real-time and rendering in UE5. Learn Sefki's photorealistic character workflows at

The Gnomon Workshop

10,334 views • 1 year ago

#NeRF is the big player nowadays and in the future 3D universe, but… why #Volinga has too much to do about it? Volinga is the first company that allows rendering NeRF in Unreal Engine 💯. This demo shows a model based on nerfacto by nerfstudio rendered in real-time.
0:18

#NeRF is the big player nowadays and in the future 3D universe, but… why #Volinga has too much to do about it? Volinga is the first company that allows rendering NeRF in Unreal Engine 💯. This demo shows a model based on nerfacto by nerfstudio rendered in real-time.

volinga.ai

94,214 views • 3 years ago

Building robots that can effectively operate alongside human workers is difficult. 🛠️ Advances in open-source physics, open foundation models, and frameworks are helping accelerate physical #AI deployment. ✔️ Newton Physics Engine, an open-source GPU-powered simulation built on OpenUSD, speeds up robot learning for advanced manipulation and mobility. ✔️ NVIDIA Cosmos Reason, an open reasoning vision language model, gives robots the ability to think like humans using prior knowledge, common sense and physics ✔️NVIDIA Isaac GR00T N1.6, an open robot foundation model, enables humanoids to understand ambiguous instructions Leading robotics developers including Agility Robotics, Lightwheel, Mentee Robotics, UniversalRobots, and Wandelbots are adopting simulation technologies and libraries to accelerate physical AI development and deployment. Omniverse Ambassador Dylan Tobin built an AI chatbot trained on Isaac Sim workflows, helping devs navigate Omniverse faster. Read the full blog 👉
0:13

Building robots that can effectively operate alongside human workers is difficult. 🛠️ Advances in open-source physics, open foundation models, and frameworks are helping accelerate physical #AI deployment. ✔️ Newton Physics Engine, an open-source GPU-powered simulation built on OpenUSD, speeds up robot learning for advanced manipulation and mobility. ✔️ NVIDIA Cosmos Reason, an open reasoning vision language model, gives robots the ability to think like humans using prior knowledge, common sense and physics ✔️NVIDIA Isaac GR00T N1.6, an open robot foundation model, enables humanoids to understand ambiguous instructions Leading robotics developers including Agility Robotics, Lightwheel, Mentee Robotics, UniversalRobots, and Wandelbots are adopting simulation technologies and libraries to accelerate physical AI development and deployment. Omniverse Ambassador Dylan Tobin built an AI chatbot trained on Isaac Sim workflows, helping devs navigate Omniverse faster. Read the full blog 👉

NVIDIA

48,500 views • 1 year ago

First Sachi 3D file is ready which you are able to use your character where you want in any metaverse, for rendering or in animation as a few example. Use the link below to try it out👇
0:16

First Sachi 3D file is ready which you are able to use your character where you want in any metaverse, for rendering or in animation as a few example. Use the link below to try it out👇

LUX

10,799 views • 3 years ago

Realistic hair and fur rendering in EEVEE, is that of any interest to you as a 3d artist? 🤭 #b3d
0:14

Realistic hair and fur rendering in EEVEE, is that of any interest to you as a 3d artist? 🤭 #b3d

Gleb Alexandrov

18,121 views • 1 year ago

i don't think people realize what just happened... Odyssey just dropped a model that learned physics without anyone teaching it no rules, no engine, it just watched the world and figured out how things move none of these clips are real, you type a prompt, it builds the world, and you can walk through it while it reacts to what you do in real time this is what ChatGPT was for language, but for the physical world
0:11

i don't think people realize what just happened... Odyssey just dropped a model that learned physics without anyone teaching it no rules, no engine, it just watched the world and figured out how things move none of these clips are real, you type a prompt, it builds the world, and you can walk through it while it reacts to what you do in real time this is what ChatGPT was for language, but for the physical world

Anatoli Kopadze

10,906 views • 18 days ago

What you’re seeing isn’t science fiction, it’s the future of robotics being trained in real time MasterBOT’s simulation engine accelerates AI learning without hardware, powered by community and data Welcome to the new era of Robotics x web3 $BOT
0:19

What you’re seeing isn’t science fiction, it’s the future of robotics being trained in real time MasterBOT’s simulation engine accelerates AI learning without hardware, powered by community and data Welcome to the new era of Robotics x web3 $BOT

MasterBOT

23,183 views • 1 year ago

Redshift 2026.6 is out Check out the new features in Maxon's GPU renderer, including support for hex tiling to minimize visible repeats in texture maps #Redshift #Redshift3D #texturing #rendering #VFX #motiongraphics @maxonvfx
0:14

Redshift 2026.6 is out Check out the new features in Maxon's GPU renderer, including support for hex tiling to minimize visible repeats in texture maps #Redshift #Redshift3D #texturing #rendering #VFX #motiongraphics @maxonvfx

CG Channel

101,563 views • 5 months ago

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.
0:19

Many 3D generators output Gaussian Splats (3DGS) for fast rendering, flexible deployment, and high visual fidelity. Static 3DGS aren't world models (no dynamics/semantics) but a true world model must allow distilling 3D-consistent representations for any given time step (3DGS/meshes). This post-distillation serves a dual purpose: 1) validates physical consistency of the model. 2) extracting explicit representations avoids continuously running a heavy generator, thus saves compute and facilitates real-time interaction.

Matthias Niessner

26,486 views • 7 months ago

Trained in Simulation Our robot learns to walk naturally similar to a human via a high fidelity physics simulator We simulate years of data in only a few hours
0:11

Trained in Simulation Our robot learns to walk naturally similar to a human via a high fidelity physics simulator We simulate years of data in only a few hours

Figure

40,777 views • 1 year ago

From simulation to reality 🤖 Robotics creator Skyentific built a walking bipedal robot using a simulation-first approach to design, test, and iterating in virtual environments before deploying in the real world. Powered by the NVIDIA Isaac platform and NVIDIA Jetson for on-device AI and control. 📖 #NationalRoboticsWeek
0:12

From simulation to reality 🤖 Robotics creator Skyentific built a walking bipedal robot using a simulation-first approach to design, test, and iterating in virtual environments before deploying in the real world. Powered by the NVIDIA Isaac platform and NVIDIA Jetson for on-device AI and control. 📖 #NationalRoboticsWeek

NVIDIA Robotics

21,868 views • 6 months ago