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.

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

1,199 subscribers

10,918 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

4 Comments

Sida Peng5 months ago

In textureless and reflective indoor environments, the reconstruction performance of Scal3R remains good.

Alvaro L5 months ago

Can you guys run a comparison with Lingbot Map, I'm genuinely curious:

Alvaro L4 months ago

Sent ya a pull request with a simple Viser visualizer. Didn't produce the best results, but maybe I'm just missing something for the proper rendering

DeeperLearner5 months ago

Great work! License?

Related Videos

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.

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

15,353 views • 16 days ago

Want to reconstruct very large-scale scenes accurately? Check out our Scal3R (CVPR'26 Highlight) — scaling up VGGT with TTT Layers: Split image sequences into chunks, compute TTT gradients per chunk, and then average gradients across chunks. Code is out:

Want to reconstruct very large-scale scenes accurately? Check out our Scal3R (CVPR'26 Highlight) — scaling up VGGT with TTT Layers: Split image sequences into chunks, compute TTT gradients per chunk, and then average gradients across chunks. Code is out:

Sida Peng

52,169 views • 5 months ago

today, we're introducing our first image model: Krea 1. Krea 1 offers superior aesthetic control and image quality. It has a wide range of artistic knowledge and supports style references and custom trainings. learn how to try our free beta 👇

today, we're introducing our first image model: Krea 1. Krea 1 offers superior aesthetic control and image quality. It has a wide range of artistic knowledge and supports style references and custom trainings. learn how to try our free beta 👇

Krea

1,181,597 views • 1 year ago

GPT Image 1.5, is live in ElevenLabs Image & Video. Stronger instruction following, precise editing capabilities, consistent visuals and 4x faster than before. Try it now for $0 on our Free plan.

GPT Image 1.5, is live in ElevenLabs Image & Video. Stronger instruction following, precise editing capabilities, consistent visuals and 4x faster than before. Try it now for $0 on our Free plan.

ElevenLabs

19,097 views • 9 months ago

Me: the Nike store doesn't have every shirt I want to try on My coworkers: say less *builds a virtual try-on feature in our app with OpenAI image models* 10 days till Boston🏃

Me: the Nike store doesn't have every shirt I want to try on My coworkers: say less builds a virtual try-on feature in our app with OpenAI image models 10 days till Boston🏃

Kyle Sanok

38,646 views • 5 months ago

🇺🇸‼️ EV EJECT HELP TO ESCAPE Apparently thee is already a product that helps you escape in such cases. PS: I just added this to my post, this is not a paid promo … but feel free to pay me. 🤣

🇺🇸‼️ EV EJECT HELP TO ESCAPE Apparently thee is already a product that helps you escape in such cases. PS: I just added this to my post, this is not a paid promo … but feel free to pay me. 🤣

Lord Bebo

33,002 views • 1 month ago

We are thrilled to announce a new feature on - Image as Pose! 🎉 This allows you to upload an image of a person as an initial image, and generate other images of people in the same pose. Get the same character in multiple poses and angles consistently🔥

We are thrilled to announce a new feature on - Image as Pose! 🎉 This allows you to upload an image of a person as an initial image, and generate other images of people in the same pose. Get the same character in multiple poses and angles consistently🔥

Leonardo.Ai

391,497 views • 3 years ago

She's such a good sport! I love to see older people enjoy themselves. It's like the older you get the younger you feel.. in some cases 😂

She's such a good sport! I love to see older people enjoy themselves. It's like the older you get the younger you feel.. in some cases 😂

iDoser

45,122 views • 5 months ago

Hy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win rate in human eval vs Hy Image3.0 Both Text to image & Image to image available. Up to 2K. Better Consistency. API: Priced for everyone. $0.024 per image on Tencent Cloud API. We only charge for what we generate — your reference images are free. Two weeks free (Only in OnSolo and Miora): Miora OnSolo Try it and tell us where it breaks.

Hy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win rate in human eval vs Hy Image3.0 Both Text to image & Image to image available. Up to 2K. Better Consistency. API: Priced for everyone. $0.024 per image on Tencent Cloud API. We only charge for what we generate — your reference images are free. Two weeks free (Only in OnSolo and Miora): Miora OnSolo Try it and tell us where it breaks.

Tencent Hy

28,412 views • 5 hours ago

🚨 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 views • 2 months ago

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

World Labs

835,502 views • 1 year ago

The Beta Test documentary was created to be a free film school for anyone to learn how we found success making movies. Here it is in full. Feel free to tag someone you love in the film industry. I'm gonna try to make one of these for all of our movies.

The Beta Test documentary was created to be a free film school for anyone to learn how we found success making movies. Here it is in full. Feel free to tag someone you love in the film industry. I'm gonna try to make one of these for all of our movies.

Jim Cummings

188,025 views • 2 years ago

Since such a large image is rather difficult to appreciate in a downsized version on twitter, I have a link on my website that allows you to zoom into the image in its entirety. Or, you can pick up one of my limited edition fine art prints!

Since such a large image is rather difficult to appreciate in a downsized version on twitter, I have a link on my website that allows you to zoom into the image in its entirety. Or, you can pick up one of my limited edition fine art prints!

Andrew McCarthy

719,714 views • 3 years ago