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.

Sparse allocation/rendering of SDF bricks is now working! The pipeline is fully GPU-driven - a series of compute shaders that manages brick allocation/baking in a 3D texture atlas, followed by draw-indirect for rendering. Still a lot more work to do, including automatic LOD.

Mike Turitzin

7,464 subscribers

39,022 views • 2 years ago •via X (Twitter)

Gaming Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Got the BVH (AABB tree) working with a nice visualization. (The circles and arrows show the hierarchy of the tree.) This is all CPU-side for now, so next is to ship the BVH to the GPU for accelerating SDF brick baking. It's already in a flat buffer so that is straightforward.

Got the BVH (AABB tree) working with a nice visualization. (The circles and arrows show the hierarchy of the tree.) This is all CPU-side for now, so next is to ship the BVH to the GPU for accelerating SDF brick baking. It's already in a flat buffer so that is straightforward.

Mike Turitzin

36,134 views • 1 year ago

Getting a bunch of questions about this! It's a full gpu rendering pipeline with built in shader editor for Rive, which can interleave 2D + 3D. Think WebGPU (minus compute, for now) that runs anywhere, not just the browser. You can implement anything at all. Cell shading. Background blurs. Deformation effects. And yes, even Rive vector components as textures. Shaders are precompiled and ship with your .riv. Minimal runtime size impact. Still WIP.

Getting a bunch of questions about this! It's a full gpu rendering pipeline with built in shader editor for Rive, which can interleave 2D + 3D. Think WebGPU (minus compute, for now) that runs anywhere, not just the browser. You can implement anything at all. Cell shading. Background blurs. Deformation effects. And yes, even Rive vector components as textures. Shaders are precompiled and ship with your .riv. Minimal runtime size impact. Still WIP.

Guido Rosso

22,346 views • 4 months ago

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

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

Gleb Alexandrov

17,787 views • 10 months ago

Is Google taking initial steps to enhance Street View? For some reason, Street View seems stuck in technology that feels outdated. I wonder if we'll see such improvements on the product side. Also, note how much better it performs in all aspects compared to Zip-NeRF in their presented material. It offers more details and fewer artifacts. Great work! "LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering" Contributions: • We propose a novel LOD representation for 3DGS which, unlike previous methods [27, 28, 17], does not recompute the list of used Gaussians at each frame. This allows for acceleration and compaction, enabling the rendering of large-scale scenes even on mobile devices. • We design a strategy to automatically select optimal hyperparameters for splitting LODs, whereas most other methods require manual tuning of hyperparameters for each 3D scene. • To further accelerate rendering, we split the scene into chunks and pre-compute sets of active Gaussians per chunk. • Finally, we introduce a novel opacity interpolation scheme to produce visually pleasing rendering and eliminate artifacts when transitioning between chunks.

Is Google taking initial steps to enhance Street View? For some reason, Street View seems stuck in technology that feels outdated. I wonder if we'll see such improvements on the product side. Also, note how much better it performs in all aspects compared to Zip-NeRF in their presented material. It offers more details and fewer artifacts. Great work! "LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering" Contributions: • We propose a novel LOD representation for 3DGS which, unlike previous methods [27, 28, 17], does not recompute the list of used Gaussians at each frame. This allows for acceleration and compaction, enabling the rendering of large-scale scenes even on mobile devices. • We design a strategy to automatically select optimal hyperparameters for splitting LODs, whereas most other methods require manual tuning of hyperparameters for each 3D scene. • To further accelerate rendering, we split the scene into chunks and pre-compute sets of active Gaussians per chunk. • Finally, we introduce a novel opacity interpolation scheme to produce visually pleasing rendering and eliminate artifacts when transitioning between chunks.

MrNeRF

62,564 views • 1 year ago

Some things don't need to be complicated. GPU compute is one of them. Pay only for what you use, nothing more. Find a GPU that works for you today:

Some things don't need to be complicated. GPU compute is one of them. Pay only for what you use, nothing more. Find a GPU that works for you today:

Theta Network

19,081 views • 1 month ago

What was a complex hacky pipeline in 2023 to take indoor 3d scans and reskin them to different types of decor is now just a few clicks in 2025. World labs marble has collapsed a lot of the complexity involved in generating and editing 3d worlds:

What was a complex hacky pipeline in 2023 to take indoor 3d scans and reskin them to different types of decor is now just a few clicks in 2025. World labs marble has collapsed a lot of the complexity involved in generating and editing 3d worlds:

Bilawal Sidhu

85,909 views • 9 months ago

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:

Shikun Liu

22,389 views • 10 months ago

🟢 News: GPU compute in the browser is finally real. WebGPU now ships by default in Chrome, Firefox, Safari, and Edge—not a polyfill, not behind a flag. You can run LLMs client-side. Transformers.js and ONNX Runtime already ship WebGPU backends. Eight years of spec work. No more asterisks. 🔗 #WebGPU #GPU #Chrome #Safari #Firefox #Edge

🟢 News: GPU compute in the browser is finally real. WebGPU now ships by default in Chrome, Firefox, Safari, and Edge—not a polyfill, not behind a flag. You can run LLMs client-side. Transformers.js and ONNX Runtime already ship WebGPU backends. Eight years of spec work. No more asterisks. 🔗 #WebGPU #GPU #Chrome #Safari #Firefox #Edge

WebGL / WebGPU

12,788 views • 6 months ago

HashPower is evolving to RAX Finance. We are building the world’s first Financial Layer for AI Compute, a specialized on-chain market where GPU capacity becomes a tradable, yield-bearing RWA. We are backed by the giants of the industry including HashKey Capital, FBG Capital, and more. Institutional grade. DeFi native. A breakdown of the vision 🧵👇

HashPower is evolving to RAX Finance. We are building the world’s first Financial Layer for AI Compute, a specialized on-chain market where GPU capacity becomes a tradable, yield-bearing RWA. We are backed by the giants of the industry including HashKey Capital, FBG Capital, and more. Institutional grade. DeFi native. A breakdown of the vision 🧵👇

RAX Finance

29,467 views • 9 months ago

The future of ANIME is Breezy. Midnight夏季Breeze is honored to receive an allocation of $ANIME by Azuki . A statement for the future. Quality comes first. The Lonely Road is paving the way for anime. Stay Breezy, stay bullish

The future of ANIME is Breezy. Midnight夏季Breeze is honored to receive an allocation of $ANIME by Azuki . A statement for the future. Quality comes first. The Lonely Road is paving the way for anime. Stay Breezy, stay bullish

Dutchtide.eth

29,722 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.

#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

94,189 views • 3 years ago

We promised to not change the core experience in Keystone, and we're sticking by that. But we did think it was worthwhile experimenting with a couple of fun, optional, extras now we have a new rendering engine. What do you think?

We promised to not change the core experience in Keystone, and we're sticking by that. But we did think it was worthwhile experimenting with a couple of fun, optional, extras now we have a new rendering engine. What do you think?

Macklebee

10,626 views • 29 days ago

KVM support is making a lot of progress. MW3 now fully runs on SteamDeck. Without Wine, without Proton. Only using This completely sandboxes the game and provides full security. Performance still needs a lot of work, but it's a smooth start

KVM support is making a lot of progress. MW3 now fully runs on SteamDeck. Without Wine, without Proton. Only using This completely sandboxes the game and provides full security. Performance still needs a lot of work, but it's a smooth start

Maurice Heumann

38,189 views • 1 month ago

Dojo is bringing Fluid Cloud Compute to Solana, enabling the foundation for future computing for worldwide applications. Start Now: In the next 60 days, Dojo will focus on global GPU access, providing a first-of-a-kind cloud framework native to Solana.

Dojo is bringing Fluid Cloud Compute to Solana, enabling the foundation for future computing for worldwide applications. Start Now: In the next 60 days, Dojo will focus on global GPU access, providing a first-of-a-kind cloud framework native to Solana.

DOAI

341,385 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/?

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

Introducing: DeCloud GPU Marketplace Dear Cloudians, We are thrilled to introduce another robust addition to the DeCloud Ecosystem, furthering our commitment to promoting decentralization at its pinnacle. The DeCloud GPU Marketplace is a cutting-edge platform designed to revolutionize the way you access and utilize GPU resources for your diverse computational needs. Users can harness the power of GPU resources for a multitude of purposes, including but not limited to: ^Mining various cryptocurrencies ^Utilizing AI/ML learning datasets ^Rendering high-resolution videos and 3D models Decentralization, Safety, and Privacy: At DeCloud, we prioritize decentralization, safety, and privacy. By providing access to different GPU providers and private connections, we ensure a secure and privacy-oriented system for our users. Your data and computational tasks are safeguarded within our decentralized DeCloud ecosystem.

Introducing: DeCloud GPU Marketplace Dear Cloudians, We are thrilled to introduce another robust addition to the DeCloud Ecosystem, furthering our commitment to promoting decentralization at its pinnacle. The DeCloud GPU Marketplace is a cutting-edge platform designed to revolutionize the way you access and utilize GPU resources for your diverse computational needs. Users can harness the power of GPU resources for a multitude of purposes, including but not limited to: ^Mining various cryptocurrencies ^Utilizing AI/ML learning datasets ^Rendering high-resolution videos and 3D models Decentralization, Safety, and Privacy: At DeCloud, we prioritize decentralization, safety, and privacy. By providing access to different GPU providers and private connections, we ensure a secure and privacy-oriented system for our users. Your data and computational tasks are safeguarded within our decentralized DeCloud ecosystem.

De Cloud

17,403 views • 2 years ago

Some performance optimizations were done in MW3 now manges to reach 60 FPS or even more, while being fully sandboxed. Still a lot to optimize, but this is a major milestone. The game is playable now 🥳

Some performance optimizations were done in MW3 now manges to reach 60 FPS or even more, while being fully sandboxed. Still a lot to optimize, but this is a major milestone. The game is playable now 🥳

Maurice Heumann

35,030 views • 1 month ago

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

AK

633,674 views • 3 years ago

The Mechanical Calculator by KingTut is a fully mechanical calculator is designed to solve times tables in seconds. Entirely 3D-printed, it requires no glue, screws, or additional hardware for working.

The Mechanical Calculator by KingTut is a fully mechanical calculator is designed to solve times tables in seconds. Entirely 3D-printed, it requires no glue, screws, or additional hardware for working.

Massimo

354,950 views • 1 month ago

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines.

Jim Fan

6,182,991 views • 2 years ago