Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Creating high quality 3DGS objects or scenes is simpler than ever, yet rendering them still lacks robust support in many toolchains. Today, we're excited to unveil Forge ( a cutting-edge 3DGS renderer that effortlessly integrates with THREE.js.

Christoph Lassner

2,777 subscribers

17,180 просмотров • 1 год назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Christoph Lassner

Christoph Lassner1 год назад

When working on Pulsar ( I saw the potential of simple primitive based representations for 3D neural rendering, reconstruction, real-time transmission and generation - but couldn't have dreamt of what it would evolve into.

Фото профиля Christoph Lassner

Christoph Lassner1 год назад

With the power of volumetric blending and Gaussian primitives, it became the powerhouse of 3D being used today across academia: with advances in surface, material and lighting reconstruction to 4D splatting for dynamic reconstruction, tracking and animation.

Фото профиля Christoph Lassner

Christoph Lassner1 год назад

Support in industry and production renderers is still evolving. Different requirements for hardware compatibility, performance and interaction with existing computer graphics and physical simulation systems are critical here. This is where Forge comes in.

Фото профиля Christoph Lassner

Christoph Lassner1 год назад

Forge is a fast, widely compatible 3DGS renderer that seamlessly integrates with THREE.js. It has been carefully designed to use WebGL2 features only to be compatible with devices more than ten years old and covering a solid 95% of internet users (

Фото профиля Christoph Lassner

Christoph Lassner1 год назад

It works correctly with other meshes and splats, multiple viewports, edits and animation. Check it out at and join us on discord . We will also participate in a 3DGS Townhall on Wednesday at 10am PDT .

Фото профиля Lab4crypto

Lab4crypto1 год назад

🚀 Don't gamble with your portfolio! Use our advanced hybrid quant risk tool using on/off-chain data and make informed decisions. 📈 Acess to 1000+ charts for your crypto journey. 📚Join our Premium Telegram for daily alerts. 📊+21 projects supported. 🏗️ Beginners and experts.

Фото профиля George Kopanas

George Kopanas1 год назад

Amazing release! Looking curiously what you are going to eventually use it for! Keep it up 🔥

Фото профиля Sumon Kabir

Sumon Kabir1 год назад

Exciting news! Forge sounds like a game-changer for 3D rendering.

Фото профиля Anthara Fairooz

Anthara Fairooz1 год назад

Exciting news! Forge seems like a game-changer for 3D rendering.

Фото профиля Altiam Kabir

Altiam Kabir1 год назад

Sounds like a game-changer! Can't wait to see the impact.

Фото профиля Sasha krecinic

Sasha krecinic1 год назад

Super cool! Well done!!

Похожие видео

This is the biggest announcement from Apple that nobody has talked about. Generating #GaussianSplatting with #AI using models like Trellis or Sam3D hasn’t made much sense...until now. Meshes are still far easier to edit, integrate cleanly into #3D workflows, and with recent retopology advances, you can get high-quality low-poly assets with detailed textures. That said, this is where the balance starts to shift toward 3DGS. Until recently, AI struggled to generate splats with proper view-dependent effects. That’s changed with LiTo, a new model from Apple that can generate 3DGS with realistic view-dependent rendering, and the results are impressive. They’re not ready for game development pipelines yet. But for VFX, e-commerce, configurators, architecture, and similar domains, the implications are significant. What would it take for you to seriously explore AI-generated 3DGS for non-gaming use cases?

This is the biggest announcement from Apple that nobody has talked about. Generating #GaussianSplatting with #AI using models like Trellis or Sam3D hasn’t made much sense...until now. Meshes are still far easier to edit, integrate cleanly into #3D workflows, and with recent retopology advances, you can get high-quality low-poly assets with detailed textures. That said, this is where the balance starts to shift toward 3DGS. Until recently, AI struggled to generate splats with proper view-dependent effects. That’s changed with LiTo, a new model from Apple that can generate 3DGS with realistic view-dependent rendering, and the results are impressive. They’re not ready for game development pipelines yet. But for VFX, e-commerce, configurators, architecture, and similar domains, the implications are significant. What would it take for you to seriously explore AI-generated 3DGS for non-gaming use cases?

Gabriele Romagnoli

20,817 просмотров • 3 месяцев назад

🚀 Excited to attend my first #NeurIPS2025 and present our lighting-aware SLAM method, NFL-BA! 🔗 🔦 Why this matters: Traditional Bundle Adjustment (BA) in SLAM assumes static lighting, but many real scenarios—endoscopy, search & rescue, subterranean robotics—use co-located light + camera, creating dynamic, near-field lighting that breaks these assumptions. ✨ What we introduce: Near-Field Lighting Bundle Adjustment Loss (NFL-BA) — a formulation that explicitly models near-field illumination inside the BA objective, allowing SLAM systems to jointly reason about geometry, appearance, and lighting. 📈 Results: Modeling lighting directly leads to ~38% improvement in mapping & tracking across dynamic-lighting sequences in both endoscopy and indoor scenes. 🧩 Plug-and-play: NFL-BA integrates seamlessly into existing neural rendering–based SLAM pipelines, using both implicit (NeRF-style) or explicit (3DGS) scene representations. 🌟 If you’re interested in SLAM, neural rendering, or illumination modeling, come check it out on Friday's poster session, 11-2pm, #4407.

🚀 Excited to attend my first #NeurIPS2025 and present our lighting-aware SLAM method, NFL-BA! 🔗 🔦 Why this matters: Traditional Bundle Adjustment (BA) in SLAM assumes static lighting, but many real scenarios—endoscopy, search & rescue, subterranean robotics—use co-located light + camera, creating dynamic, near-field lighting that breaks these assumptions. ✨ What we introduce: Near-Field Lighting Bundle Adjustment Loss (NFL-BA) — a formulation that explicitly models near-field illumination inside the BA objective, allowing SLAM systems to jointly reason about geometry, appearance, and lighting. 📈 Results: Modeling lighting directly leads to ~38% improvement in mapping & tracking across dynamic-lighting sequences in both endoscopy and indoor scenes. 🧩 Plug-and-play: NFL-BA integrates seamlessly into existing neural rendering–based SLAM pipelines, using both implicit (NeRF-style) or explicit (3DGS) scene representations. 🌟 If you’re interested in SLAM, neural rendering, or illumination modeling, come check it out on Friday's poster session, 11-2pm, #4407.

Roni Sengupta

21,162 просмотров • 8 месяцев назад

Generate image, 3D, and video from a single sketch in one click in ComfyUI with AI! I’m excited to share a cutting-edge workflow I’ve developed that combines inside ComfyUI: Runway with fal. ai api (yes there is a node for it :) ), Stable AI’s stable fast 3D , powerful Flux, ControlNet, IPAdapter, Gemini LLm in ComfyUI. This innovation allows you to generate high-quality visuals and 3D models, reposition objects, and create videos—completely automated from a simple sketch input. Would you link a tutorial for it ? #AI #ComfyUI #3DModeling #Automation #CreativeTech

Generate image, 3D, and video from a single sketch in one click in ComfyUI with AI! I’m excited to share a cutting-edge workflow I’ve developed that combines inside ComfyUI: Runway with fal. ai api (yes there is a node for it :) ), Stable AI’s stable fast 3D , powerful Flux, ControlNet, IPAdapter, Gemini LLm in ComfyUI. This innovation allows you to generate high-quality visuals and 3D models, reposition objects, and create videos—completely automated from a simple sketch input. Would you link a tutorial for it ? #AI #ComfyUI #3DModeling #Automation #CreativeTech

Lovis Odin

36,789 просмотров • 1 год назад

Today is Moms Equal Pay Day. Too many women who balance work and caregiving are still navigating systems that were never built by them, or with them in mind. Moms are the backbone of our economy, yet they continue to face persistent pay gaps contributing to an overall wealth gap.

Today is Moms Equal Pay Day. Too many women who balance work and caregiving are still navigating systems that were never built by them, or with them in mind. Moms are the backbone of our economy, yet they continue to face persistent pay gaps contributing to an overall wealth gap.

Jennifer Siebel Newsom

10,981 просмотров • 1 год назад

A moving dialogue from the late Ian Richardson that would apply to so many of us today. Ian, upon reaching the summit of Arthur’s Seat in Edinburgh, reflects on the past and his place in it. Today, such reflections are more depressing than ever. Our purpose is to live in the knowledge that we're leaving behind a better world which is why so many good people today are dying with broken hearts.

A moving dialogue from the late Ian Richardson that would apply to so many of us today. Ian, upon reaching the summit of Arthur’s Seat in Edinburgh, reflects on the past and his place in it. Today, such reflections are more depressing than ever. Our purpose is to live in the knowledge that we're leaving behind a better world which is why so many good people today are dying with broken hearts.

Vinnie Sullivan

89,593 просмотров • 8 месяцев назад

Vidu Q3 is now available on Akool! Meet the powerful next-gen video generator that turns your ideas into cinematic, high-quality videos in minutes. Create dynamic scenes Generate synchronized visuals and audio Bring stories to life with rich motion and realism From creative storytelling to marketing content, Vidu Q3 gives you the freedom to make any video you imagine, faster and easier than ever. Start creating today and experience the future of AI video.

Vidu Q3 is now available on Akool! Meet the powerful next-gen video generator that turns your ideas into cinematic, high-quality videos in minutes. Create dynamic scenes Generate synchronized visuals and audio Bring stories to life with rich motion and realism From creative storytelling to marketing content, Vidu Q3 gives you the freedom to make any video you imagine, faster and easier than ever. Start creating today and experience the future of AI video.

Akool Inc

1,935,351 просмотров • 6 месяцев назад

🚨 Democrats Literally CONFIRM The Great Replacement Theory ON CAMERA & Some People Still Don’t Believe It Chuck Schumer “Now more than ever, we're short of workers. We have a population that is not reproducing it on its own with the same level that it used to, the only way we're gonna have a great future in America is if we welcome and embrace immigrants, the dreamers, and all of them. Because our ultimate goal is to help the dreamers, but get a path to citizenship for all 11,000,000 or however many undocumented there are here.”

🚨 Democrats Literally CONFIRM The Great Replacement Theory ON CAMERA & Some People Still Don’t Believe It Chuck Schumer “Now more than ever, we're short of workers. We have a population that is not reproducing it on its own with the same level that it used to, the only way we're gonna have a great future in America is if we welcome and embrace immigrants, the dreamers, and all of them. Because our ultimate goal is to help the dreamers, but get a path to citizenship for all 11,000,000 or however many undocumented there are here.”

Wall Street Apes

572,870 просмотров • 2 лет назад

We're proud to showcase some recent real-time work with 3D / 4D Gaussian splatting. In January of 2024 we acquired a full 3DGS commercial license with Inria to allow us to offer 4DGS services to clients around the world. We've spent the last 10 months developing our custom 4DGS software pipeline, utilizing our own Nvidia GPU cluster to batch process 100,000's of 4DGS frames rapidly, combined with our state-of-the-art custom built volumetric capture system(s). We can capture anything from complex character interactions for visual effects shots, or dynamic fast fighting scenes, sports, acting, even capturing and storing memories of family and friends for the future! The possibilities are endless. Our focus is always on high-quality and high-fidelity. We don't cut corners and we're continually striving to learn and improve. The below video showcases some 6-dof spatial captures we took of Henry Pearce's family. These scenes are played back in real-time @ 30fps inside a 3rd party engine running in a 120fps virtual environment. This is a culmination of years of hard work and dedication and we are keen to commercialize this technology with you. Please do reach out if you're interested in our capture systems or our 3D/4DGS processing services. HQ YouTube Link: HQ Vimeo Link: #spatialcapture #vr #virtualmemories #inria #3dgs #4dgs #aeonx #ir #ximea Music "Vision" by megiddo music Special thanks to Aras Pranckevičius 🇺🇦🇱🇹

We're proud to showcase some recent real-time work with 3D / 4D Gaussian splatting. In January of 2024 we acquired a full 3DGS commercial license with Inria to allow us to offer 4DGS services to clients around the world. We've spent the last 10 months developing our custom 4DGS software pipeline, utilizing our own Nvidia GPU cluster to batch process 100,000's of 4DGS frames rapidly, combined with our state-of-the-art custom built volumetric capture system(s). We can capture anything from complex character interactions for visual effects shots, or dynamic fast fighting scenes, sports, acting, even capturing and storing memories of family and friends for the future! The possibilities are endless. Our focus is always on high-quality and high-fidelity. We don't cut corners and we're continually striving to learn and improve. The below video showcases some 6-dof spatial captures we took of Henry Pearce's family. These scenes are played back in real-time @ 30fps inside a 3rd party engine running in a 120fps virtual environment. This is a culmination of years of hard work and dedication and we are keen to commercialize this technology with you. Please do reach out if you're interested in our capture systems or our 3D/4DGS processing services. HQ YouTube Link: HQ Vimeo Link: #spatialcapture #vr #virtualmemories #inria #3dgs #4dgs #aeonx #ir #ximea Music "Vision" by megiddo music Special thanks to Aras Pranckevičius 🇺🇦🇱🇹

Infinite-Realities

203,384 просмотров • 2 лет назад

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,762 просмотров • 4 месяцев назад

3D was either pretty, or fast. Now it’s BOTH! Meet Interactive Scenes built with Gaussian Splatting: 🔥Browser & Phone-Friendly: Hyperefficient and fast rendering everywhere 👌Embed Anywhere: 8-20MB streaming files (even smaller soon!) ✨Ultra High Quality offline NeRF renders & mesh exports 🍕Creating is as easy as capturing a video on your phone Available TODAY in Luma iOS App, Luma Web, as well as the Luma API. And fully commercially usable. Get Started for Free → #lumaai #3d #ai #gaussainsplatting #nerf

3D was either pretty, or fast. Now it’s BOTH! Meet Interactive Scenes built with Gaussian Splatting: 🔥Browser & Phone-Friendly: Hyperefficient and fast rendering everywhere 👌Embed Anywhere: 8-20MB streaming files (even smaller soon!) ✨Ultra High Quality offline NeRF renders & mesh exports 🍕Creating is as easy as capturing a video on your phone Available TODAY in Luma iOS App, Luma Web, as well as the Luma API. And fully commercially usable. Get Started for Free → #lumaai #3d #ai #gaussainsplatting #nerf

Luma

528,804 просмотров • 2 лет назад

Gov. Abigail Spanberger: The idea that you are paying more than a mortgage to have your children in quality childcare is an issue that impacts all of us. It is not sustainable and frankly it's not acceptable. What I'm signing today is a response to the reality that we face as a Commonwealth. We're creating the Employee Child Care Assistance Program, a new tool that incentivizes employers to help their employees pay for childcare with the state matching those contributions. This is one of the ways that we can make childcare more affordable without putting the entire burden on families or on the government alone.

Gov. Abigail Spanberger: The idea that you are paying more than a mortgage to have your children in quality childcare is an issue that impacts all of us. It is not sustainable and frankly it's not acceptable. What I'm signing today is a response to the reality that we face as a Commonwealth. We're creating the Employee Child Care Assistance Program, a new tool that incentivizes employers to help their employees pay for childcare with the state matching those contributions. This is one of the ways that we can make childcare more affordable without putting the entire burden on families or on the government alone.

Headquarters

45,830 просмотров • 2 месяцев назад

Tomorrow’s #WorldHealthDay is a cause for celebration, and a call to action. More mothers and children are surviving today than ever before. But still, every 7 seconds, a mother or baby dies a preventable death. That is why World Health Organization (WHO), UNICEF and UNFPA launched the “Every Woman, Every Newborn, Everywhere” partnership, and the Child Survival Action initiative, to support national and local health systems in stopping preventable deaths.

Tomorrow’s #WorldHealthDay is a cause for celebration, and a call to action. More mothers and children are surviving today than ever before. But still, every 7 seconds, a mother or baby dies a preventable death. That is why World Health Organization (WHO), UNICEF and UNFPA launched the “Every Woman, Every Newborn, Everywhere” partnership, and the Child Survival Action initiative, to support national and local health systems in stopping preventable deaths.

Tedros Adhanom Ghebreyesus

12,308 просмотров • 1 год назад

Excited to announce that I've shipped my first game! Written from the ground up in Three.js in 3 months and published on VIVERSE Official Some tech stuff that I'm really proud of: - fully custom spherical harmonics prt lighting. Giving a baked diffuse look while still allowing for dynamic objects - Runs completely inside a WebWorker (rendering & simulation) using OffscreenCanvas - Supports all input types: desktop, mobile, gamepad (non-trivial if your app runs in a worker!) - No Postprocessing! No bloom - everything you see is faked via mesh based shaders for performance reasons Huge thanks to VIVERSE Official who have made this possible by letting me into their Creator Program. It's not easy to make a living off gamedev on the web yet, so this is great for the ecosystem. All links below: #VIVERSE #threejs #IndieGameDev

Excited to announce that I've shipped my first game! Written from the ground up in Three.js in 3 months and published on VIVERSE Official Some tech stuff that I'm really proud of: - fully custom spherical harmonics prt lighting. Giving a baked diffuse look while still allowing for dynamic objects - Runs completely inside a WebWorker (rendering & simulation) using OffscreenCanvas - Supports all input types: desktop, mobile, gamepad (non-trivial if your app runs in a worker!) - No Postprocessing! No bloom - everything you see is faked via mesh based shaders for performance reasons Huge thanks to VIVERSE Official who have made this possible by letting me into their Creator Program. It's not easy to make a living off gamedev on the web yet, so this is great for the ecosystem. All links below: #VIVERSE #threejs #IndieGameDev

Brian Breiholz

14,587 просмотров • 1 год назад

$Need Ads That Convert? At UGC Factory, we embrace a systematic approach to creative, which allows us to deliver high-quality ads at a fraction of what our competitors charge. 🚀 Our secret? A robust roster of handpicked creators, data-driven strategies, and an in-house team of video editors. 💡 Our edge? We don't just create; we analyze, learn, and adapt. With insights from 40 different meta ad managers across our portfolio, we're ahead of the curve, seeing systematically what's working across the board. 📈 Whether you're a budding brand or a white-label agency, we're here to deliver the creative punch you need - without burning a hole in your pocket. 🎯$

Need Ads That Convert? At UGC Factory, we embrace a systematic approach to creative, which allows us to deliver high-quality ads at a fraction of what our competitors charge. 🚀 Our secret? A robust roster of handpicked creators, data-driven strategies, and an in-house team of video editors. 💡 Our edge? We don't just create; we analyze, learn, and adapt. With insights from 40 different meta ad managers across our portfolio, we're ahead of the curve, seeing systematically what's working across the board. 📈 Whether you're a budding brand or a white-label agency, we're here to deliver the creative punch you need - without burning a hole in your pocket. 🎯

Dan Ragan

47,901 просмотров • 3 лет назад

Public opinion has shifted dramatically over the past three years, but politics is still struggling to catch up. More people than ever have witnessed the destruction in Gaza in real time. That has changed how many understand Israel, Palestine, occupation and accountability. Yet governments, including Australia's, continue to support Israel in ways that don't reflect that shift in public sentiment. A clip from the new episode of The Antony Loewenstein Podcast, out now on Youtube, Spotify and Apple. Produced by @lenaahelou and Lem:

Public opinion has shifted dramatically over the past three years, but politics is still struggling to catch up. More people than ever have witnessed the destruction in Gaza in real time. That has changed how many understand Israel, Palestine, occupation and accountability. Yet governments, including Australia's, continue to support Israel in ways that don't reflect that shift in public sentiment. A clip from the new episode of The Antony Loewenstein Podcast, out now on Youtube, Spotify and Apple. Produced by @lenaahelou and Lem:

Antony Loewenstein

11,686 просмотров • 12 дней назад

“Nigeria Is The Easiest Place To Be a Billionaire. How Many People Do You Know That Left Nigeria For The UK Or Abroad And Became Billionaires? They Go There To Survive, Not To Be Rich. Most Of Them Go There To Do Care Jobs, Yet Your Ambition Is To Japa From Nigeria To Join Them In Modern Slavery. Some Even Sold Their Properties In Nigeria To Go And Rent Houses Abroad, And Till Today They Suffering And Still Haven’t Made It.” ~ Pastor Dalapo

“Nigeria Is The Easiest Place To Be a Billionaire. How Many People Do You Know That Left Nigeria For The UK Or Abroad And Became Billionaires? They Go There To Survive, Not To Be Rich. Most Of Them Go There To Do Care Jobs, Yet Your Ambition Is To Japa From Nigeria To Join Them In Modern Slavery. Some Even Sold Their Properties In Nigeria To Go And Rent Houses Abroad, And Till Today They Suffering And Still Haven’t Made It.” ~ Pastor Dalapo

Somto Okonkwo

52,151 просмотров • 2 месяцев назад

Q. What if you fall truly in love with someone? 🐻Love is still a mystery to me. 🐻Have I ever been in love? 🐻It makes me wonder if I could ever love someone so deeply, to the point I feel like I'd die, that I would put everything aside just for them- I've never experienced that yet. - He's so real for saying this bc I think that's something that many people out there would resonate with, regardless of their age and stage in life 🥹

Q. What if you fall truly in love with someone? 🐻Love is still a mystery to me. 🐻Have I ever been in love? 🐻It makes me wonder if I could ever love someone so deeply, to the point I feel like I'd die, that I would put everything aside just for them- I've never experienced that yet. - He's so real for saying this bc I think that's something that many people out there would resonate with, regardless of their age and stage in life 🥹

Lia K

28,672 просмотров • 1 месяц назад

Theatrical modern cuisine is the worst thing to ever happen to fine dining. As someone who will travel specifically for food, it's an insult. I'm thoroughly convinced the chefs are all just pulling an elaborate prank on their customers and seeing how ridiculous they can get while still charging a fortune. I don't want an interactive dining experience outside of me cutting and eating the food. I don't want a deconstructed ice cream sundae or peeled grapes. Serve me a meal made with fresh, high-quality ingredients with balanced flavors. I'm not impressed that you have a Pacojet in the kitchen.

Theatrical modern cuisine is the worst thing to ever happen to fine dining. As someone who will travel specifically for food, it's an insult. I'm thoroughly convinced the chefs are all just pulling an elaborate prank on their customers and seeing how ridiculous they can get while still charging a fortune. I don't want an interactive dining experience outside of me cutting and eating the food. I don't want a deconstructed ice cream sundae or peeled grapes. Serve me a meal made with fresh, high-quality ingredients with balanced flavors. I'm not impressed that you have a Pacojet in the kitchen.

9mmSMG

78,614 просмотров • 8 месяцев назад

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

Anderson Mancini

23,984 просмотров • 2 месяцев назад