Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

Open-source 3D from a few random photos. No camera poses. No special capture. #UniForge3D takes a handful of unposed shots, keeps what the photos actually show, and generates the missing parts into one complete textured model. Reconstruction + generation in the same space. Best photo per region. Textured GLB... show more

Stefan 3D AI

15,411 subscribers

29,856 görüntüleme • 23 gün önce •via X (Twitter)

Bilim & Teknoloji #UniForge3D

Anya Rossi• Live Now

Private livecam show

6 Yorum

TTX profil fotoğrafı

TTX23 gün önce

I feel like it is not a good time to start making a game as if it will be far easiser next month and iluvatar knows what happens after that ...

Zoe profil fotoğrafı

Zoe23 gün önce

👍

Alex profil fotoğrafı

Alex23 gün önce

Awesome!

Spookie profil fotoğrafı

Spookie22 gün önce

Pixel3D or this one ?

고마마 profil fotoğrafı

고마마23 gün önce

이거 공간도 되는건가요? 아님 오브젝트 형태의 것들만 되는건가요?

pmlstk profil fotoğrafı

pmlstk22 gün önce

how fair assessment can there be with all your paid 3d service sponsorships

Benzer Videolar

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

30,407 görüntüleme • 3 ay önce

Pixel-perfect 3D generation is here. 🧵 Tencent’s new Free Local Pixal3D project every pixel directly into 3D space. No more "AI hallucinations"—just sub-pixel faithful reconstruction. ✅ Open Weights ✅ Local (24GB VRAM) ✅ Matches silhouettes perfectly Is this the new benchmark for open-source 3D? Full workflow and test: 👇 #3DAI #Pixal3D #GameDev #Tencen #OpenSource #3DModeling

Pixel-perfect 3D generation is here. 🧵 Tencent’s new Free Local Pixal3D project every pixel directly into 3D space. No more "AI hallucinations"—just sub-pixel faithful reconstruction. ✅ Open Weights ✅ Local (24GB VRAM) ✅ Matches silhouettes perfectly Is this the new benchmark for open-source 3D? Full workflow and test: 👇 #3DAI #Pixal3D #GameDev #Tencen #OpenSource #3DModeling

Stefan 3D AI

23,210 görüntüleme • 5 ay önce

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

287,034 görüntüleme • 3 ay önce

💚 NVIDIA has released the MotionBricks weights on the Hugging Face Hub! MotionBricks generates real-time motion for game characters and humanoid robots. Give it a character's recent poses and the poses it should reach next, and it generates the movement in between, at 15,000 FPS with 2 ms latency. - One model trained on 350K+ motion clips - Smart Primitives for navigation and object interaction, no retraining - SOMA weights for human characters - Unitree G1 weights for the humanoid robot - Code under Apache 2.0, weights under the NVIDIA Open Model Agreement Animation and robotics motion generation, now open for anyone to build on!

💚 NVIDIA has released the MotionBricks weights on the Hugging Face Hub! MotionBricks generates real-time motion for game characters and humanoid robots. Give it a character's recent poses and the poses it should reach next, and it generates the movement in between, at 15,000 FPS with 2 ms latency. - One model trained on 350K+ motion clips - Smart Primitives for navigation and object interaction, no retraining - SOMA weights for human characters - Unitree G1 weights for the humanoid robot - Code under Apache 2.0, weights under the NVIDIA Open Model Agreement Animation and robotics motion generation, now open for anyone to build on!

Alvaro Bartolome

201,839 görüntüleme • 12 gün önce

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Elliott / Shangzhe Wu

107,391 görüntüleme • 2 yıl önce

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image. orange = input image in 3D space blue = camera moving through the scene

Ian Curtis

10,580 görüntüleme • 23 gün önce

3D scene reconstruction works great until the camera never sees part of the scene. ArtiFixer from NVIDIA Research is an open autoregressive model that fills in the missing geometry that other methods leave blank. #SIGGRAPH2026 paper, code + demo:

3D scene reconstruction works great until the camera never sees part of the scene. ArtiFixer from NVIDIA Research is an open autoregressive model that fills in the missing geometry that other methods leave blank. #SIGGRAPH2026 paper, code + demo:

NVIDIA AI

155,889 görüntüleme • 4 ay önce

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,960 görüntüleme • 1 yıl önce

Wow. No more waiting hours for COLMAP / SfM — you get live 3D Gaussian Splats straight from unposed images, even for massive scenes. Your 3D scene and camera poses are ready right as you finish capturing. Inria team cooked again; code drops end of May.

Wow. No more waiting hours for COLMAP / SfM — you get live 3D Gaussian Splats straight from unposed images, even for massive scenes. Your 3D scene and camera poses are ready right as you finish capturing. Inria team cooked again; code drops end of May.

Bilawal Sidhu

48,530 görüntüleme • 1 yıl önce

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now

Vaishnavi

356,091 görüntüleme • 6 ay önce

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

109,958 görüntüleme • 1 ay önce

Free Local Image-to-3D Now Keeps Your Text and Logos Readable, Even at 5K Faces Image to 3D Lab turns a single image into a textured 3D model on your own machine. The new Pixel Match update copies the real pixels from your picture back onto the model. Highlights: • Text and logos stay readable, even at ~5K faces (down from ~900K) • Low-poly models you can rig and animate • Runs locally on Mac or NVIDIA • Free and open source, no API or credits GitHub:

Free Local Image-to-3D Now Keeps Your Text and Logos Readable, Even at 5K Faces Image to 3D Lab turns a single image into a textured 3D model on your own machine. The new Pixel Match update copies the real pixels from your picture back onto the model. Highlights: • Text and logos stay readable, even at ~5K faces (down from ~900K) • Low-poly models you can rig and animate • Runs locally on Mac or NVIDIA • Free and open source, no API or credits GitHub:

Stefan 3D AI

25,179 görüntüleme • 1 ay önce

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)

Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image. Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

223,362 görüntüleme • 9 gün önce

Photos are about to feel like postcards. Every photo of a place is taken from where someone else stood. This street, captured by Hugh Hou on the Insta360 X6, lets you pick the spot. I walked it myself: the jester statue, the red phone boxes, the mural, a stranger in a white dress frozen mid-road. A short 360° clip is all it takes. The Insta360 Spatial Capture turns it into a 3D space you can explore. No scanning rig, no reconstruction software. That's why this feels bigger than a feature. We went from photos to videos, and now to whole spaces. Remembering a place can mean walking back into it. There are places from my life I only have a few photos of. I'd give a lot to stand in them once more and look where I want. It goes well beyond memories: → Take the Tesla Roadster display at the Petersen Automotive Museum. Capture it once and anyone can walk around the car long after the display ends → Property tours you can stand inside → One neighborhood, captured every few years Tell me the first place you'd keep. Link below 👇

Photos are about to feel like postcards. Every photo of a place is taken from where someone else stood. This street, captured by Hugh Hou on the Insta360 X6, lets you pick the spot. I walked it myself: the jester statue, the red phone boxes, the mural, a stranger in a white dress frozen mid-road. A short 360° clip is all it takes. The Insta360 Spatial Capture turns it into a 3D space you can explore. No scanning rig, no reconstruction software. That's why this feels bigger than a feature. We went from photos to videos, and now to whole spaces. Remembering a place can mean walking back into it. There are places from my life I only have a few photos of. I'd give a lot to stand in them once more and look where I want. It goes well beyond memories: → Take the Tesla Roadster display at the Petersen Automotive Museum. Capture it once and anyone can walk around the car long after the display ends → Property tours you can stand inside → One neighborhood, captured every few years Tell me the first place you'd keep. Link below 👇

Luqman Ali

63,497 görüntüleme • 10 gün önce

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference code, data pipelines, and architecture—yours to fine-tune! ✅ Runs on consumer GPUs, empowering creators, devs, and small teams. Be the first to shape the future of 3D! Download now and build something epic. Model: Demo: Github: Hunyuan 3D Creation Engine: #Hunyuan3D #OpenSource #3DCreation

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference code, data pipelines, and architecture—yours to fine-tune! ✅ Runs on consumer GPUs, empowering creators, devs, and small teams. Be the first to shape the future of 3D! Download now and build something epic. Model: Demo: Github: Hunyuan 3D Creation Engine: #Hunyuan3D #OpenSource #3DCreation

Tencent Hy

236,506 görüntüleme • 1 yıl önce

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Yang You

245,856 görüntüleme • 2 yıl önce

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

Alexandre Morgand

15,192 görüntüleme • 8 ay önce

Interesting take on world model consistency: what if you skip 3D reconstruction entirely? WorldCrafter from TencentARC, weights are open. Instead of building 3D geometry, the video generator queries an implicit memory by camera pose. point the camera somewhere and the memory fills in the view. → one image or text prompt, minutes of scene exploration. base and distilled fast version both on HF → 384×640 for now. resolution can scale once the architecture works ✍️full paper at 🤗weights at ⌨️code at

Interesting take on world model consistency: what if you skip 3D reconstruction entirely? WorldCrafter from TencentARC, weights are open. Instead of building 3D geometry, the video generator queries an implicit memory by camera pose. point the camera somewhere and the memory fills in the view. → one image or text prompt, minutes of scene exploration. base and distilled fast version both on HF → 384×640 for now. resolution can scale once the architecture works ✍️full paper at 🤗weights at ⌨️code at

Tencent AI

12,142 görüntüleme • 1 ay önce

🚨 Forget LIDAR. The Robbyant team just dropped a streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. One single camera. Runs in real time. Open-source. Entirely end-to-end. NO iterative optimization tricks and no post-processing cleanup steps! It outperforms both existing streaming approaches and several offline methods. 100% Free and open-source. Repo, paper and model weights in 🧵↓

🚨 Forget LIDAR. The Robbyant team just dropped a streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. One single camera. Runs in real time. Open-source. Entirely end-to-end. NO iterative optimization tricks and no post-processing cleanup steps! It outperforms both existing streaming approaches and several offline methods. 100% Free and open-source. Repo, paper and model weights in 🧵↓

Charly Wargnier ♨️

36,285 görüntüleme • 4 ay önce

Integrate camera features into your Flutter apps for iOS, Android, and Web 📸 The `camera` package lets you display a live preview, capture photos, and record videos.

Integrate camera features into your Flutter apps for iOS, Android, and Web 📸 The `camera` package lets you display a live preview, capture photos, and record videos.

Flutter

24,161 görüntüleme • 1 yıl önce