Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing MegaSaM! 🎥 Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes! MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

zhengqi_li's profile picture

Zhengqi Li

1,586 subscribers

56,923 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Zhengqi Li
Zhengqi Livor 1 Jahr

🔗See the gallery of results, and try our interactive viewer at 📄Read more: Big thanks to the amazing team! @holynski_, @forrestercole , @QianqianWang5, @jin_linyi, @vickie_ye_, @akanazawa, @Jimantha and Richard Tucker

Profilbild von Soumith Chintala
Soumith Chintalavor 1 Jahr

when will the code be released? would love to try it

Profilbild von Angela Dai
Angela Daivor 1 Jahr

looks super cool :)

Profilbild von Bilawal Sidhu
Bilawal Sidhuvor 1 Jahr

impressive -- results looks much better than monst3r too -- congrats!

Profilbild von Taro TheTechie
Taro TheTechievor 1 Jahr

Impressive! I'm curious to see how MegaSaM handles complex scenes with multiple moving objects. Can it maintain accuracy in those scenarios?

Profilbild von Nigel Higgs
Nigel Higgsvor 1 Jahr

jesus christ this field is moving fast. The weights availble?

Profilbild von Jonathan Sauder
Jonathan Saudervor 1 Jahr

Very impressive results, congratulations! Looking forward to the code/checkpoint release!

Profilbild von Ang Cao
Ang Caovor 1 Jahr

So cool

Ähnliche Videos

I'm excited to share our new work Align3R that estimates camera poses and consistent depth maps from a monocular video of a dynamic scene. Project page: Code: Paper:
1:12

I'm excited to share our new work Align3R that estimates camera poses and consistent depth maps from a monocular video of a dynamic scene. Project page: Code: Paper:

Yuan Liu

56,547 Aufrufe • vor 1 Jahr

"DVD: Dynamic Video Depth" TL;DR: Recovers temporally consistent depth from monocular videos using diffusion priors + geometric constraints, handling dynamic scenes and motion robustly.
0:36

"DVD: Dynamic Video Depth" TL;DR: Recovers temporally consistent depth from monocular videos using diffusion priors + geometric constraints, handling dynamic scenes and motion robustly.

Alexandre Morgand

11,804 Aufrufe • vor 2 Monaten

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos Contributions: • An incremental joint optimization approach for simultaneous camera pose and 3DGS reconstruction, reducing local minima and ensuring global consistency. • A robust pose estimation module leveraging learned 3D priors for accurate camera pose estimation. • An adaptive Octree Anchor Formation strategy that significantly reduces memory usage while preserving reconstruction quality.
0:23

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos Contributions: • An incremental joint optimization approach for simultaneous camera pose and 3DGS reconstruction, reducing local minima and ensuring global consistency. • A robust pose estimation module leveraging learned 3D priors for accurate camera pose estimation. • An adaptive Octree Anchor Formation strategy that significantly reduces memory usage while preserving reconstruction quality.

MrNeRF

35,969 Aufrufe • vor 9 Monaten

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.
0:39

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Stability AI

197,203 Aufrufe • vor 1 Jahr

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses
0:48

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses

AK

73,258 Aufrufe • vor 3 Jahren

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.
0:22

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,521 Aufrufe • vor 9 Monaten

Thrilled to introduce Video Depth Anything to support Depth Estimation for super-long videos (over 5 minutes). 👉It enjoys all the benefits of #DepthAnything: high-quality, fast, robust, etc. Proj Page:
1:28

Thrilled to introduce Video Depth Anything to support Depth Estimation for super-long videos (over 5 minutes). 👉It enjoys all the benefits of #DepthAnything: high-quality, fast, robust, etc. Proj Page:

Bingyi Kang

25,464 Aufrufe • vor 1 Jahr

Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: Huge congrats to everyone involved and the community 🎉
0:41

Exciting news! MegaSAM code is out🔥 & the updated Shape of Motion results with MegaSAM are really impressive! A year ago I didn't think we could make any progress on these videos: Huge congrats to everyone involved and the community 🎉

Angjoo Kanazawa

95,476 Aufrufe • vor 1 Jahr

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.
0:25

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Jerrod Lew

26,972 Aufrufe • vor 8 Monaten

CamCloneMaster: replicating camera movements from reference videos without needing camera parameters; based on Wan2.1-1.3B; built using a large-scale Camera Clone Dataset. Solid results.
0:48

CamCloneMaster: replicating camera movements from reference videos without needing camera parameters; based on Wan2.1-1.3B; built using a large-scale Camera Clone Dataset. Solid results.

Wildminder

16,829 Aufrufe • vor 7 Monaten

Introducing PixVerse 5.5 Now with 10-second videos, native audio generation, dynamic multi-clip camera work, and smarter prompt optimization Available now on Freepik
0:31

Introducing PixVerse 5.5 Now with 10-second videos, native audio generation, dynamic multi-clip camera work, and smarter prompt optimization Available now on Freepik

Freepik

10,415 Aufrufe • vor 5 Monaten

🚨Dynamic Camera Tutorial🚨 Struggling to get dynamic camera movements in your AI videos? We cracked the code! 🚀 Here's how we craft dynamic videos with stunning results using a Master Prompt Template for ChatGPT (or any other LLM) that incorporates dynamic camera movements! Creative process + examples 👇 Sound On 🔉
0:33

🚨Dynamic Camera Tutorial🚨 Struggling to get dynamic camera movements in your AI videos? We cracked the code! 🚀 Here's how we craft dynamic videos with stunning results using a Master Prompt Template for ChatGPT (or any other LLM) that incorporates dynamic camera movements! Creative process + examples 👇 Sound On 🔉

Nim

36,987 Aufrufe • vor 1 Jahr

🎥✨Camera Motion is here in Dream Machine 1.6! Effortlessly direct text-to-video and image-to-video scenes with simple commands! Just type in ‘camera’ to unlock camera motions! Imagine in #LumaDreamMachine 🎬🚀
0:30

🎥✨Camera Motion is here in Dream Machine 1.6! Effortlessly direct text-to-video and image-to-video scenes with simple commands! Just type in ‘camera’ to unlock camera motions! Imagine in #LumaDreamMachine 🎬🚀

Luma

260,896 Aufrufe • vor 1 Jahr

New Video! Excited to share our work on fast view synthesis of casual videos. 🤩 high-quality dynamic view synthesis 🤩 applicable for a wide range of casual videos 🤩 fast training and rendering
1:02

New Video! Excited to share our work on fast view synthesis of casual videos. 🤩 high-quality dynamic view synthesis 🤩 applicable for a wide range of casual videos 🤩 fast training and rendering

Jia-Bin Huang

27,360 Aufrufe • vor 2 Jahren

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.
0:30

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.

MrNeRF

25,651 Aufrufe • vor 1 Jahr

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction
1:03

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction

Junyi Zhang @CVPR

131,523 Aufrufe • vor 1 Jahr

Some additional scenes from Kyiv. All videos are from the same security camera.
1:01

Some additional scenes from Kyiv. All videos are from the same security camera.

AMK Mapping 🇳🇿

11,575 Aufrufe • vor 9 Monaten

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:
0:25

Can video generative models exhibit visuospatial intelligence? 🤔 Introducing Video4Spatial — a video-only framework that tackles spatial tasks. With just video context, our model can: 🔍 Ground objects by planning geometry-consistent paths 📸 Follow camera-pose instructions for scene navigation 🌐 Generalize to long contexts & unseen outdoor scenes A step toward video models as visual-spatial reasoners. Project: arXiv:

Xingang Pan

15,902 Aufrufe • vor 5 Monaten

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper
1:13

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper

Marktechpost AI Dev News ⚡

217,453 Aufrufe • vor 8 Monaten