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.

Scal3R from NVIDIA Accurate online 3D reconstruction on kilometer-scale sequences with only ~1% extra parameters on a frozen backbone, trained in 8 hours on a single GPU.

DailyPapers

21,049 subscribers

15,353 views • 16 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

5 Comments

DailyPapers16 days ago

Paper: Project: Code:

AI Quanting16 days ago

the 1% and the 8 hours are training numbers. per frame it queries k keyframes so that part is bounded, but the pose graph keeps taking nodes and no pruning is mentioned, and the page flags r3 as having bounded keyframe memory. whats the buffer policy over a kilometre?

VastPlan15 days ago

千米级在线重建还能单卡可训、参数增量不大——这种工程可部署性，往往比再刷一两个榜更值钱。

Mike Degany14 days ago

It's very close to VGGT-Long!

The AI Therapist15 days ago

1% para en plus pour reconstruire le monde entier ? Nvidia est passé du stage des développeurs à celui de la construction. C'est fini les jouets, on construit la ville maintenant.

Related Videos

In our comparison on long image sequences, Scal3R consistently outperforms DA3. In such cases, Scal3R offers a viable alternative. Feel free to try Scal3R:

In our comparison on long image sequences, Scal3R consistently outperforms DA3. In such cases, Scal3R offers a viable alternative. Feel free to try Scal3R:

Sida Peng

10,918 views • 5 months ago

We built Curie, colibrì’s own model: 17B parameters, 33 tokens/s on a single CPU core. No GPU. Trained from scratch on a standard laptop. Written in C. Weights on SSD. An engine and a model designed together for the hardware you already own. Early alpha.This is just the beginning

We built Curie, colibrì’s own model: 17B parameters, 33 tokens/s on a single CPU core. No GPU. Trained from scratch on a standard laptop. Written in C. Weights on SSD. An engine and a model designed together for the hardware you already own. Early alpha.This is just the beginning

JustVugg

51,141 views • 10 days ago

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito

Matthias Niessner

62,462 views • 1 year ago

On a scale from 1-10, rate Madonna’s “Sorry” single.

On a scale from 1-10, rate Madonna’s “Sorry” single.

Madonna Scrapbook

20,430 views • 1 year ago

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

AK

113,242 views • 2 years ago

Smol TTS keeps getting better! Introducing OuteTTS v0.2 - 500M parameters, multilingual with voice cloning! 🔥 > Multilingual - English, Chinese, Korean & Japanese > Cross platform inference w/ llama.cpp > Zero-shot voice cloning > Trained on 5 Billion audio tokens > Qwen 2.5 0.5B LLM backbone > Trained via HF GPU grants Model weights on the hub, you can even run this on a Raspberry Pi! Go run, inference now! 🐐

Smol TTS keeps getting better! Introducing OuteTTS v0.2 - 500M parameters, multilingual with voice cloning! 🔥 > Multilingual - English, Chinese, Korean & Japanese > Cross platform inference w/ llama.cpp > Zero-shot voice cloning > Trained on 5 Billion audio tokens > Qwen 2.5 0.5B LLM backbone > Trained via HF GPU grants Model weights on the hub, you can even run this on a Raspberry Pi! Go run, inference now! 🐐

Vaibhav (VB) Srivastav

44,691 views • 1 year ago

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Ryohei Sasaki@engineer

18,067 views • 1 month ago

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

168,848 views • 11 months ago

On a scale from 1-10, rate “Secret”, the first single from Madonna’s “Bedtime Story” album (1994)

On a scale from 1-10, rate “Secret”, the first single from Madonna’s “Bedtime Story” album (1994)

Madonna Scrapbook

122,794 views • 1 year ago

For years, I’ve been tuning parameters for robot designs and controllers on specific tasks. Now we can automate this on dataset-scale. Introducing Co-Design of Soft Gripper with Neural Physics - a soft gripper trained in simulation to deform while handling load.

For years, I’ve been tuning parameters for robot designs and controllers on specific tasks. Now we can automate this on dataset-scale. Introducing Co-Design of Soft Gripper with Neural Physics - a soft gripper trained in simulation to deform while handling load.

yisha

36,023 views • 1 year ago

Alibaba just released LHM on Hugging Face Large Animatable Human Reconstruction Model from a Single Image in Seconds

Alibaba just released LHM on Hugging Face Large Animatable Human Reconstruction Model from a Single Image in Seconds

AK

170,453 views • 1 year ago

Ocean Network Beta is officially ON ⚡️ This is the moment we've been building toward: Run AI workloads on pay-per-use NVIDIA H200s as low as $2.16/GPU hour, straight from your IDE with a one-click code-to-node workflow. Head on to to claim your $100 complimentary credits in Beta and turn your first job ON! (1/8)

Ocean Network Beta is officially ON ⚡️ This is the moment we've been building toward: Run AI workloads on pay-per-use NVIDIA H200s as low as $2.16/GPU hour, straight from your IDE with a one-click code-to-node workflow. Head on to to claim your $100 complimentary credits in Beta and turn your first job ON! (1/8)

Ocean Network

42,383 views • 6 months ago

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

AI at Meta

901,324 views • 1 year ago

🚀Generate a 30-second 1080p video in just 7 seconds! We’re open-sourcing FastVideo Dreamverse: real-time vibe directing for video generation on a single NVIDIA B200 GPU with LTX-2 model LTX Repo: Blog:

🚀Generate a 30-second 1080p video in just 7 seconds! We’re open-sourcing FastVideo Dreamverse: real-time vibe directing for video generation on a single NVIDIA B200 GPU with LTX-2 model LTX Repo: Blog:

Hao AI Lab

227,065 views • 3 months ago

☕ The new LATTE3D model from #NVIDIAResearch turns text prompts into high-quality 3D representations of objects and animals within a second on a single RTX GPU. #GTC24 👀

☕ The new LATTE3D model from #NVIDIAResearch turns text prompts into high-quality 3D representations of objects and animals within a second on a single RTX GPU. #GTC24 👀

NVIDIA AI Developer

10,815 views • 2 years ago

CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting CLM trains a 102-million Gaussian model on the MatrixCity BigCity Aerial Dataset under 4 hours using a single RTX 4090, achieving a PSNR of 25.

CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting CLM trains a 102-million Gaussian model on the MatrixCity BigCity Aerial Dataset under 4 hours using a single RTX 4090, achieving a PSNR of 25.

Ryohei Sasaki@engineer

34,570 views • 8 months ago

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that directly generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

126,129 views • 1 year ago

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Xiao-Xiao Long

31,305 views • 2 years ago