Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

The SuperSplat 3DGS Viewer is now Open Source! 🙌 🏃 Tip-top load times and performance 🥽 AR + VR support 🎥 Orbit and fly cameras 🎬 Camera flythrough animations Your 3D Gaussian Splats never looked so good. ✨ Read more:

Will Eastcott

9,457 subscribers

31,163 görüntüleme • 1 yıl önce •via X (Twitter)

Sanat Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

8 Yorum

Will Eastcott profil fotoğrafı

Will Eastcott1 yıl önce

3DGS in the video created by the world-class splat scanner Christoph Schindelar:

PowerBeatsVR profil fotoğrafı

PowerBeatsVR3 yıl önce

Get ready for a full-body VR workout that’s fun, fast, and intuitive — Play PowerBeatsVR (Now on Meta Quest) 🔥

Abdullah Hamdi profil fotoğrafı

Abdullah Hamdi1 yıl önce

Awesome work, and great news ! How easy is it to integrate new methods , like our convex splatting ?

Will Eastcott profil fotoğrafı

Will Eastcott1 yıl önce

Always excited to hear proposals for upgrading the core implementation of 3DGS in the PlayCanvas Engine. Personally, I'd recommend opening an issue on the Engine to discuss this in more detail:

Rafael Spring profil fotoğrafı

Rafael Spring1 yıl önce

Amazing work, super thrilled about this. Keep it up! 🔥

softyoda profil fotoğrafı

softyoda1 yıl önce

Wow amazing ! 🔥🔥🔥

noquierocoima profil fotoğrafı

noquierocoima1 yıl önce

What si the default.json?

Will Eastcott profil fotoğrafı

Will Eastcott1 yıl önce

Are you asking about this:

Benzer Videolar

✨ Announcing SuperSplat 2.0 ✨ Your open source platform for 3DGS 🌐 Publish your splats to the web 🎥 Create cool camera flythroughs 🧑‍🤝‍🧑 Explore splats from the community 🥽 Immerse yourself with AR and VR Links 👇

✨ Announcing SuperSplat 2.0 ✨ Your open source platform for 3DGS 🌐 Publish your splats to the web 🎥 Create cool camera flythroughs 🧑‍🤝‍🧑 Explore splats from the community 🥽 Immerse yourself with AR and VR Links 👇

Will Eastcott

58,741 görüntüleme • 1 yıl önce

✨SuperSplat 1.13.0 is here✨ Open source 3D Gaussian Splat Editor 🏃 Support for loading and playback of 4DGS (AKA animated gaussian splats) TRY SUPERSPLAT:

✨SuperSplat 1.13.0 is here✨ Open source 3D Gaussian Splat Editor 🏃 Support for loading and playback of 4DGS (AKA animated gaussian splats) TRY SUPERSPLAT:

Will Eastcott

76,833 görüntüleme • 1 yıl önce

✨SuperSplat 1.12.0 is here✨ Open source 3D Gaussian Splat Editor 📋 Copy and paste selections 🤳 AR mode in exported HTML Viewer TRY NOW:

✨SuperSplat 1.12.0 is here✨ Open source 3D Gaussian Splat Editor 📋 Copy and paste selections 🤳 AR mode in exported HTML Viewer TRY NOW:

Will Eastcott

12,928 görüntüleme • 1 yıl önce

SuperSplat 2.7.0 is here! 🚀 Your open source editor for 3D Gaussian Splats ✨ This release overhauls the export options for your projects. Now you get fine grained control over spherical harmonics bands, splat selection and more. TRY NOW:

SuperSplat 2.7.0 is here! 🚀 Your open source editor for 3D Gaussian Splats ✨ This release overhauls the export options for your projects. Now you get fine grained control over spherical harmonics bands, splat selection and more. TRY NOW:

Will Eastcott

13,458 görüntüleme • 1 yıl önce

SuperSplat v2.17.0 is here! ✨ Your free and open source 3D Gaussian Splat Editor. 🗜️ Export to the super-compressed SOG format 🪽 Fly camera controls (WASD) 🎞️ Newly linked tutorial video from Radiance Fields 🪄 UI polish [1 / 2]

SuperSplat v2.17.0 is here! ✨ Your free and open source 3D Gaussian Splat Editor. 🗜️ Export to the super-compressed SOG format 🪽 Fly camera controls (WASD) 🎞️ Newly linked tutorial video from Radiance Fields 🪄 UI polish [1 / 2]

Will Eastcott

16,565 görüntüleme • 7 ay önce

2D is what the camera sees.👀 3D is what the world is. 🌍 Today, we’re proudly open-sourcing QuerySplat — an open-source feed-forward 3D model that turns a few unposed images into a navigable 3D scene in seconds (run on 4090🪶). Your input: a few unposed images Our output: a sharp, navigable 3D scene — generated in seconds! 🚀 🧠 organize scenes with 3D queries, not pixel-bound Gaussians 📷 no camera poses or manual calibration required ⚡ reconstruct new scenes in a single forward pass ✨ preserve sharp geometry and high-frequency appearance 🏆 achieve state-of-the-art results on DL3DV-Evaluation 🔓 code and model weights are now open-source From pixels to scenes, we are making 3D generation scalable. Try our free iOS app — it’s a lot of fun! 😆 🔗 Try it on the Web: 🔗 Paper: 🔗 Code & weights: 🔗 Project page: 🔗 #AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

2D is what the camera sees.👀 3D is what the world is. 🌍 Today, we’re proudly open-sourcing QuerySplat — an open-source feed-forward 3D model that turns a few unposed images into a navigable 3D scene in seconds (run on 4090🪶). Your input: a few unposed images Our output: a sharp, navigable 3D scene — generated in seconds! 🚀 🧠 organize scenes with 3D queries, not pixel-bound Gaussians 📷 no camera poses or manual calibration required ⚡ reconstruct new scenes in a single forward pass ✨ preserve sharp geometry and high-frequency appearance 🏆 achieve state-of-the-art results on DL3DV-Evaluation 🔓 code and model weights are now open-source From pixels to scenes, we are making 3D generation scalable. Try our free iOS app — it’s a lot of fun! 😆 🔗 Try it on the Web: 🔗 Paper: 🔗 Code & weights: 🔗 Project page: 🔗 #AIGC #3DGS #AI #Computervision #3D #artist #3dartist #3d

InSpatio｜影溯

29,524 görüntüleme • 28 gün önce

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.( Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 🔗GitHub: 🤗HuggingFace: 📝Technical Details:

Tencent Hy

198,391 görüntüleme • 1 yıl önce

HUGE UPDATE My twitch 3d livestream is now in VR and AR! We've basically made a hologram that can be shrunk down to sit on your desk!!! The 3d livestream is a real-time interactive point cloud (built using LiDAR cameras) of me, synced up with my regular twitch broadcasts. It's full 360, uses no avatars or assets, and has integrated twitch features such as chat, a movie screen with the normal 2D stream displayed, and customizable sprite characters that viewers can control and move freely about the space with AND they show up on the regular stream as if in the room with me. We've recently gotten collision working so I can swat viewers away and send them flying, added a racing minigame with hoops that also show up in the normal stream, and ultimately made VR / AR HOLOGRAMS I'm so excited and it's only gonna get better. We're adding more interactive features, working on better aesthetics, and creating REAL NON-VR holograms that can ACTUALLY sit on your desk!! I can't wait Follow the project here and on and swing by if you have any questions or if you want to join future playtests (please do ahaha) :)

HUGE UPDATE My twitch 3d livestream is now in VR and AR! We've basically made a hologram that can be shrunk down to sit on your desk!!! The 3d livestream is a real-time interactive point cloud (built using LiDAR cameras) of me, synced up with my regular twitch broadcasts. It's full 360, uses no avatars or assets, and has integrated twitch features such as chat, a movie screen with the normal 2D stream displayed, and customizable sprite characters that viewers can control and move freely about the space with AND they show up on the regular stream as if in the room with me. We've recently gotten collision working so I can swat viewers away and send them flying, added a racing minigame with hoops that also show up in the normal stream, and ultimately made VR / AR HOLOGRAMS I'm so excited and it's only gonna get better. We're adding more interactive features, working on better aesthetics, and creating REAL NON-VR holograms that can ACTUALLY sit on your desk!! I can't wait Follow the project here and on and swing by if you have any questions or if you want to join future playtests (please do ahaha) :)

Perri

39,904 görüntüleme • 1 yıl önce

SOMEONE JUST MADE TRAVEL AGENCIES OBSOLETE A guy walked through London with a camera on his head, uploaded a file, and now anyone on the planet can walk those same streets right in their browser without a ticket, hotel, or visa. Click -> you're there. Every cobblestone, every brick, every shadow between the buildings - exactly as it is in real life. The numbers break your brain: - Average London trip: $2,000-5,000 - Cost to make this scan: ~$200 - File size: smaller than a Netflix episode — File size: smaller than a Netflix episode The science is even wilder. It's called 3D Gaussian Splatting - instead of polygons like in video games, it uses millions of tiny glowing "splats" of color and depth, and AI reconstructs reality straight from your photos. The result opens on your phone and feels like teleportation. And the business opportunity is completely insane. People are already charging $500–2,000 per location for hotels, museums, restaurants, architecture firms - everyone wants this and almost nobody knows how to do it yet. One phone and one day in a city creates content that lives forever, and the whole thing is open source. London is no longer across the ocean. It's in your browser tab.

SOMEONE JUST MADE TRAVEL AGENCIES OBSOLETE A guy walked through London with a camera on his head, uploaded a file, and now anyone on the planet can walk those same streets right in their browser without a ticket, hotel, or visa. Click -> you're there. Every cobblestone, every brick, every shadow between the buildings - exactly as it is in real life. The numbers break your brain: - Average London trip: $2,000-5,000 - Cost to make this scan: ~$200 - File size: smaller than a Netflix episode — File size: smaller than a Netflix episode The science is even wilder. It's called 3D Gaussian Splatting - instead of polygons like in video games, it uses millions of tiny glowing "splats" of color and depth, and AI reconstructs reality straight from your photos. The result opens on your phone and feels like teleportation. And the business opportunity is completely insane. People are already charging $500–2,000 per location for hotels, museums, restaurants, architecture firms - everyone wants this and almost nobody knows how to do it yet. One phone and one day in a city creates content that lives forever, and the whole thing is open source. London is no longer across the ocean. It's in your browser tab.

Noisy

14,806 görüntüleme • 3 ay önce

🥟: Annyeo~ 🙍‍♀️: 铉辰 (Hyunjin)， listen to me carefully. You are my favorite artist. I love your dancing and performance. VMA, Play with Fire, Motley Crew, Mic&Brush, TASTE, 樂, Psycho, and so many more. You are the best dancer, the professional. I love your strong performance, mad, passionate, and sexy. I love your music too. So Good, Long For You, Cover Me, Red Lights, TASTE, Quill Pen, Love untold, untitled, and so many more. I love your ambition and independence. You can do anything. You are a genius! 🥟: Yeah, I’m genius~ 🙍‍♀️: Now, I’ll tell you what we want. We want you to have confidence and believe in yourself. You are the brightest star. Be yourself and shine bright. We love your stage performance, singing, rapping, and dance break. We miss your dance content and dance lives so much. We look forward to your future album, your concert, your art gallery, and maybe your movie. Remember that you are the best, you deserve the best, and you have so much potential. Be healthy. Be happy. Be free. The reality can be hard, but you have so many fans who love you and support you. Never stop chasing your dreams. We can wait, and we still have time. You are so humble, but you should be more proud of yourself. You have so many talents and achievements. You are a legend, a role model, the main character. Have confidence and believe in yourself. Do you promise? Staff: Time is up. 🥟: Awwwww, thank you! 🙍‍♀️: Do you promise? 🥟: Promise (pinky promise). Thank you. Staff: Time is up. 🥟: You are the best!

🥟: Annyeo~ 🙍‍♀️: 铉辰 (Hyunjin)， listen to me carefully. You are my favorite artist. I love your dancing and performance. VMA, Play with Fire, Motley Crew, Mic&Brush, TASTE, 樂, Psycho, and so many more. You are the best dancer, the professional. I love your strong performance, mad, passionate, and sexy. I love your music too. So Good, Long For You, Cover Me, Red Lights, TASTE, Quill Pen, Love untold, untitled, and so many more. I love your ambition and independence. You can do anything. You are a genius! 🥟: Yeah, I’m genius~ 🙍‍♀️: Now, I’ll tell you what we want. We want you to have confidence and believe in yourself. You are the brightest star. Be yourself and shine bright. We love your stage performance, singing, rapping, and dance break. We miss your dance content and dance lives so much. We look forward to your future album, your concert, your art gallery, and maybe your movie. Remember that you are the best, you deserve the best, and you have so much potential. Be healthy. Be happy. Be free. The reality can be hard, but you have so many fans who love you and support you. Never stop chasing your dreams. We can wait, and we still have time. You are so humble, but you should be more proud of yourself. You have so many talents and achievements. You are a legend, a role model, the main character. Have confidence and believe in yourself. Do you promise? Staff: Time is up. 🥟: Awwwww, thank you! 🙍‍♀️: Do you promise? 🥟: Promise (pinky promise). Thank you. Staff: Time is up. 🥟: You are the best!

Hyunjin 현진 Central 🍀

371,602 görüntüleme • 11 ay önce

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Bilawal Sidhu

704,124 görüntüleme • 1 yıl önce

SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. Open source. Built on PlayCanvas. Free GitHub:

SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. Open source. Built on PlayCanvas. Free GitHub:

AdiiX

9,738,526 görüntüleme • 3 ay önce

🚨 SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. 100% Open source. Built on PlayCanvas.

🚨 SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. 100% Open source. Built on PlayCanvas.

ZoAina

1,520,521 görüntüleme • 3 ay önce

.Dwarkesh Patel: By 2030, it will be less expensive to monitor every single nook and cranny in America than it is to remodel the White House. “Mass surveillance is, at least in certain forms, already legal. It has just been impractical to enforce so far. Under current law, you have no Fourth Amendment protection against any data you share with a third party. That includes your bank, your ISP, your phone carrier, and your email provider. The government reserves the right to purchase and read this data in bulk without a warrant. What’s been missing is the ability to actually do anything with all of this data — no agency has the manpower to monitor every single camera, read every single message, and cross-reference every single transaction. However, that bottleneck goes away with AI. There are 100 million CCTV cameras in America. You can get pretty good open source multimodal models for 10 cents per million input tokens. So if you process a frame every ten seconds, and each frame is 1,000 tokens, then for 30 billion dollars, you can process every single camera in America. And remember that a given level of AI ability gets 10x cheaper every single year - so a year from now it’ll cost 3 billion, and then a year after 300 million, and by 2030, it’ll be less expensive to monitor every single nook and cranny in this country than it is to remodel the White House. Once the technical capacity for mass surveillance and political suppression exists, the only thing standing between us and an authoritarian state is the political expectation that this is not something we do here.”

.Dwarkesh Patel: By 2030, it will be less expensive to monitor every single nook and cranny in America than it is to remodel the White House. “Mass surveillance is, at least in certain forms, already legal. It has just been impractical to enforce so far. Under current law, you have no Fourth Amendment protection against any data you share with a third party. That includes your bank, your ISP, your phone carrier, and your email provider. The government reserves the right to purchase and read this data in bulk without a warrant. What’s been missing is the ability to actually do anything with all of this data — no agency has the manpower to monitor every single camera, read every single message, and cross-reference every single transaction. However, that bottleneck goes away with AI. There are 100 million CCTV cameras in America. You can get pretty good open source multimodal models for 10 cents per million input tokens. So if you process a frame every ten seconds, and each frame is 1,000 tokens, then for 30 billion dollars, you can process every single camera in America. And remember that a given level of AI ability gets 10x cheaper every single year - so a year from now it’ll cost 3 billion, and then a year after 300 million, and by 2030, it’ll be less expensive to monitor every single nook and cranny in this country than it is to remodel the White House. Once the technical capacity for mass surveillance and political suppression exists, the only thing standing between us and an authoritarian state is the political expectation that this is not something we do here.”

Arjun Khemani

145,706 görüntüleme • 5 ay önce

🚀 The Future of 3D Creation is Here! World Labs World Labs dropped a bombshell with #Marble, and the spatial computing world is buzzing. 🤯 👉 For Beginners: Create stunning 3D worlds, no code needed. 👉 For Pros: Power-up your workflow with advanced tools. 👉 For Industry: Marks a milestone in Spatial AI innovation! But let's talk about the elephant in the room: Hardware. 🖥️ While #Marble leverages cloud power to generate worlds in seconds, accessing and sharing them still depends heavily on local device performance. 𝗧𝗵𝗲 𝗖𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲𝘀 𝗔𝗿𝗲 𝗥𝗲𝗮𝗹: ➤ 𝗔𝗰𝗰𝗲𝘀𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝘆: Basic laptops struggle to run initial generations smoothly — not to mention high-fidelity scenes. Sharable links are a step forward, but must every viewer own high-end hardware? ➤ 𝗠𝗼𝗯𝗶𝗹𝗲 𝗚𝗮𝗽: Full creation tools aren’t mobile-ready yet. Desktop is still a must for the complete experience. ➤ 𝗩𝗥 "𝗩𝗶𝗲𝘄𝗶𝗻𝗴": "Open in VR" is a great start—but true collaborative VR requires serious rendering power and device support. How do we include everyone, without top-tier headsets or perfect networks? We tested #Marble on a typical Windows laptop. See the performance gap? We bring fluid Marble experience via #LarkXR! 👀 ▶︎ 𝗙𝗹𝗶𝗽 𝘁𝗵𝗲 𝗦𝘄𝗶𝘁𝗰𝗵 #LarkXR is here. Our Cloud XR Streaming Technology delivers high-fidelity VR and 3D experiences to any device — breaking through hardware limits and compatibility gaps. Now every user can join, view, and collaborate seamlessly. #Marble Unlocks Spatial World Creation. #LarkXR Unlocks Interactive Immersive Accessibility. 𝘓𝘦𝘵'𝘴 𝘸𝘰𝘳𝘬 𝘵𝘰𝘨𝘦𝘵𝘩𝘦𝘳 𝘵𝘰 𝘦𝘯𝘴𝘶𝘳𝘦 𝘦𝘷𝘦𝘳𝘺𝘰𝘯𝘦, 𝘦𝘷𝘦𝘳𝘺𝘸𝘩𝘦𝘳𝘦, 𝘰𝘯 𝘢𝘯𝘺 𝘥𝘦𝘷𝘪𝘤𝘦, 𝘤𝘢𝘯 𝘵𝘳𝘶𝘭𝘺 𝘴𝘵𝘦𝘱 𝘪𝘯𝘵𝘰 𝘵𝘩𝘦 𝘸𝘰𝘳𝘭𝘥𝘴 𝘺𝘰𝘶 𝘤𝘳𝘦𝘢𝘵𝘦. 𝗚𝗲𝘁 𝗦𝘁𝗮𝗿𝘁𝗲𝗱 𝗪𝗶𝘁𝗵 𝗟𝗮𝗿𝗸𝗫𝗥 𝗧𝗼𝗱𝗮𝘆 🚀 🚀 🚀 #WorldLabs

🚀 The Future of 3D Creation is Here! World Labs World Labs dropped a bombshell with #Marble, and the spatial computing world is buzzing. 🤯 👉 For Beginners: Create stunning 3D worlds, no code needed. 👉 For Pros: Power-up your workflow with advanced tools. 👉 For Industry: Marks a milestone in Spatial AI innovation! But let's talk about the elephant in the room: Hardware. 🖥️ While #Marble leverages cloud power to generate worlds in seconds, accessing and sharing them still depends heavily on local device performance. 𝗧𝗵𝗲 𝗖𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲𝘀 𝗔𝗿𝗲 𝗥𝗲𝗮𝗹: ➤ 𝗔𝗰𝗰𝗲𝘀𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝘆: Basic laptops struggle to run initial generations smoothly — not to mention high-fidelity scenes. Sharable links are a step forward, but must every viewer own high-end hardware? ➤ 𝗠𝗼𝗯𝗶𝗹𝗲 𝗚𝗮𝗽: Full creation tools aren’t mobile-ready yet. Desktop is still a must for the complete experience. ➤ 𝗩𝗥 "𝗩𝗶𝗲𝘄𝗶𝗻𝗴": "Open in VR" is a great start—but true collaborative VR requires serious rendering power and device support. How do we include everyone, without top-tier headsets or perfect networks? We tested #Marble on a typical Windows laptop. See the performance gap? We bring fluid Marble experience via #LarkXR! 👀 ▶︎ 𝗙𝗹𝗶𝗽 𝘁𝗵𝗲 𝗦𝘄𝗶𝘁𝗰𝗵 #LarkXR is here. Our Cloud XR Streaming Technology delivers high-fidelity VR and 3D experiences to any device — breaking through hardware limits and compatibility gaps. Now every user can join, view, and collaborate seamlessly. #Marble Unlocks Spatial World Creation. #LarkXR Unlocks Interactive Immersive Accessibility. 𝘓𝘦𝘵'𝘴 𝘸𝘰𝘳𝘬 𝘵𝘰𝘨𝘦𝘵𝘩𝘦𝘳 𝘵𝘰 𝘦𝘯𝘴𝘶𝘳𝘦 𝘦𝘷𝘦𝘳𝘺𝘰𝘯𝘦, 𝘦𝘷𝘦𝘳𝘺𝘸𝘩𝘦𝘳𝘦, 𝘰𝘯 𝘢𝘯𝘺 𝘥𝘦𝘷𝘪𝘤𝘦, 𝘤𝘢𝘯 𝘵𝘳𝘶𝘭𝘺 𝘴𝘵𝘦𝘱 𝘪𝘯𝘵𝘰 𝘵𝘩𝘦 𝘸𝘰𝘳𝘭𝘥𝘴 𝘺𝘰𝘶 𝘤𝘳𝘦𝘢𝘵𝘦. 𝗚𝗲𝘁 𝗦𝘁𝗮𝗿𝘁𝗲𝗱 𝗪𝗶𝘁𝗵 𝗟𝗮𝗿𝗸𝗫𝗥 𝗧𝗼𝗱𝗮𝘆 🚀 🚀 🚀 #WorldLabs

Paraverse

16,000 görüntüleme • 9 ay önce

GeoLibre v2.0.0 is here! GeoLibre is a free and open-source geospatial platform that runs everywhere: as a native desktop app, in the browser, on Android, and embedded right inside Jupyter notebooks. It brings modern web mapping, cloud-native data formats, and a full processing toolbox together in one place, all built on MapLibre and with no proprietary lock-in. Our first major release adds a true 3D globe, takes mapping beyond Earth to Mars and the Moon, lets styles round-trip with QGIS, and turns loaded vector layers into editable, save-back-to-source data. What's new in v2.0.0 - Planetary mapping: explore Mars, the Moon, and other bodies with the OpenPlanetaryMap basemaps, a per-project ellipsoid, and a planet switcher right in the Layers panel. - CesiumJS 3D globe: switch any map pane to a photorealistic 3D globe that stays camera-synced with your 2D maps and mirrors the layer stack. - True 3D data: render vector layers with Z coordinates, load TIN/MultiPatch 3D shapefiles, and display KML/KMZ Collada (.dae) 3D models. - Symbology interchange: import and export vector styling as OGC SLD, QGIS QML, and Mapbox GL style JSON, so styles round-trip between GeoLibre, QGIS, and the Mapbox/MapLibre ecosystem. - Editable source layers: edit vector layers and write the changes back to their source, including GeoPackage and GeoJSON files and PostGIS database tables. - Weather and sky: a new Weather menu with live cloud and precipitation radar overlays (RainViewer), plus a Google Earth-style sun position simulation for realistic lighting. - Terrain and lighting: double-click the terrain control to set vertical exaggeration, and view any scene in true 3D relief. - Smarter data import: bring in CSV without coordinates as an attribute table, split GPX track points and route points into separate layers, and load macOS-zipped and projected-CRS shapefiles. - Raster in the browser: build normalized-difference indices for any HTTP COG and extract COG/WMS/XYZ bounding-box subsets client-side. - Field Calculator upgrades: compute geometry length and area directly on your features. - Attribute table: multi-select rows with Ctrl and Shift, plus faster navigation. - Google Earth-style extras: "View in Google Maps / Google Earth" actions, camera-reset keyboard shortcuts, and a UTM easting/northing grid mode for the Gridlines overlay. - New plugins: a Mapillary coverage and street-level image viewer, a Historical Imagery panel, and an Elevation Profile tool. - Fully localized: all 13 language catalogs are complete, so the entire UI is translatable. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: #GIS #GeospatialData #OpenSource #RemoteSensing #DataVisualization #MapLibre #GeoLibre

Qiusheng Wu

35,991 görüntüleme • 1 ay önce

Your our history shouldn’t be taught in a boring way 🫠 I’ve always loved history, but I could never imagine what life actually looked like back then. So I built Empire Atlas, a 3D interactive explorer of 8 historical empires using Three.js and Kimi.ai K3 🔥 It lets you explore how people lived, what their homes looked like, their maps, daily life, interiors, and more. Properly researched. But the craziest part is that this was near one shot vibe coded with Kimi K3 🤯 When I previously built a 3D anatomy app with GPT 5.6 sol, I had to iterate on performance and optimization. With Kimi, the moment I handed over the 3D assets (generated using Tripo), prompt and design (by GPT Image 2.0), it created an 11 step engineering plan to build the entire thing. The very first step it did was optimizing the assets. It took nearly 500MB of 3D assets and brought them down to just 17.8MB using mesh simplification, Draco compression, and 1024px WebP textures. Absolutely nuts. It also generated 56 historical images across the 8 empires showing daily life, maps, interiors, and more using its image plugin with batch processing. Those were converted to WebP too, bringing the total image size to around 10MB. That’s a huge reason the experience loads so fast on website. It's engineering workflow or intelligence has really impressed me so far. The only downside is that it took more than 5 hours, though 😅 Anyway, back to history. In Empire Atlas, you can explore 8 different empires and see how people and our ancestors lived at that time. I really love those textures I was able to create using Tripo. You can explore their homes in 3D, and there’s so much more we could do with this. We could extend these houses into fully explorable interiors and create increasingly realistic reconstructions of what life actually looked like. And maybe create fun education games too. I genuinely think this can make history education so much more immersive. Much more than showing black and white images in boring textbooks. Go explore your history now 👇 Live: Code:

Your our history shouldn’t be taught in a boring way 🫠 I’ve always loved history, but I could never imagine what life actually looked like back then. So I built Empire Atlas, a 3D interactive explorer of 8 historical empires using Three.js and Kimi.ai K3 🔥 It lets you explore how people lived, what their homes looked like, their maps, daily life, interiors, and more. Properly researched. But the craziest part is that this was near one shot vibe coded with Kimi K3 🤯 When I previously built a 3D anatomy app with GPT 5.6 sol, I had to iterate on performance and optimization. With Kimi, the moment I handed over the 3D assets (generated using Tripo), prompt and design (by GPT Image 2.0), it created an 11 step engineering plan to build the entire thing. The very first step it did was optimizing the assets. It took nearly 500MB of 3D assets and brought them down to just 17.8MB using mesh simplification, Draco compression, and 1024px WebP textures. Absolutely nuts. It also generated 56 historical images across the 8 empires showing daily life, maps, interiors, and more using its image plugin with batch processing. Those were converted to WebP too, bringing the total image size to around 10MB. That’s a huge reason the experience loads so fast on website. It's engineering workflow or intelligence has really impressed me so far. The only downside is that it took more than 5 hours, though 😅 Anyway, back to history. In Empire Atlas, you can explore 8 different empires and see how people and our ancestors lived at that time. I really love those textures I was able to create using Tripo. You can explore their homes in 3D, and there’s so much more we could do with this. We could extend these houses into fully explorable interiors and create increasingly realistic reconstructions of what life actually looked like. And maybe create fun education games too. I genuinely think this can make history education so much more immersive. Much more than showing black and white images in boring textbooks. Go explore your history now 👇 Live: Code:

The Bugged Dev

119,099 görüntüleme • 20 gün önce

🎬 Global Launch: Dreamina Seedance 2.5 is now live! Our most cinematic video model yet has arrived, and Dreamina AI is your official platform. Step into a new era of precision control and long-take storytelling: · Native 30s videos in a single generation · A new interactive editing experience: reshape any part of the frame · Long video mode: up to 3 minutes, with consistency that holds throughout · Dreamina AI plugins for Maya and Blender, built for film-grade production pipelines · Up to 50 multimodal references, now with support for 3D white models and green-screen footage — bringing AI generation into real production workflows · More true-to-life lighting and shadows, richer motion detail, and precise timestamp control down to 1 second Dreamina Seedance 2.5 is more than a model. It's an upgrade to what you can create. Now open to Dreamina AI subscribers. 🕐 Available now across Southeast Asia, the Middle East, Africa, Europe, and South America. More countries and regions coming soon. ✨ Watch Aura Design in action with the new model ⏳ Limited time: save up to 32% on credits per generation 🎁 Repost and comment – first 300 users get 1,000 credits in 12 hours #DreaminaSeedance25 #DreaminaAI

🎬 Global Launch: Dreamina Seedance 2.5 is now live! Our most cinematic video model yet has arrived, and Dreamina AI is your official platform. Step into a new era of precision control and long-take storytelling: · Native 30s videos in a single generation · A new interactive editing experience: reshape any part of the frame · Long video mode: up to 3 minutes, with consistency that holds throughout · Dreamina AI plugins for Maya and Blender, built for film-grade production pipelines · Up to 50 multimodal references, now with support for 3D white models and green-screen footage — bringing AI generation into real production workflows · More true-to-life lighting and shadows, richer motion detail, and precise timestamp control down to 1 second Dreamina Seedance 2.5 is more than a model. It's an upgrade to what you can create. Now open to Dreamina AI subscribers. 🕐 Available now across Southeast Asia, the Middle East, Africa, Europe, and South America. More countries and regions coming soon. ✨ Watch Aura Design in action with the new model ⏳ Limited time: save up to 32% on credits per generation 🎁 Repost and comment – first 300 users get 1,000 credits in 12 hours #DreaminaSeedance25 #DreaminaAI

Dreamina AI

619,452 görüntüleme • 1 ay önce