正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵

Anton Obukhov

2,676 subscribers

49,820 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 次观看 • 1 年前

Spent some time this week playing with depth estimation models. Monocular depth estimation has come a long way, but in terms of metric accuracy and geometric consistency, stereo depth still has it beat by a wide margin. DepthPro (mono) vs FoundationStereo (stereo)

Spent some time this week playing with depth estimation models. Monocular depth estimation has come a long way, but in terms of metric accuracy and geometric consistency, stereo depth still has it beat by a wide margin. DepthPro (mono) vs FoundationStereo (stereo)

FrostyFridge

27,774 次观看 • 1 年前

🛹🛹⌐◨-◨🛹🛹 We're so thrilled to announce our mint Date and Time ⭐️⭐️ Please check our announcement channel in Discord for more info

🛹🛹⌐◨-◨🛹🛹 We're so thrilled to announce our mint Date and Time ⭐️⭐️ Please check our announcement channel in Discord for more info

Nounish Punk

30,291 次观看 • 2 年前

🤔Applying Depth Estimation models directly to videos can result in inconsistency between frames. 💪Well, not anymore. 🔥ChronoDepth is a new approach to video depth estimation that focuses on achieving both accuracy within each frame and consistency across frames. 📜More👇

🤔Applying Depth Estimation models directly to videos can result in inconsistency between frames. 💪Well, not anymore. 🔥ChronoDepth is a new approach to video depth estimation that focuses on achieving both accuracy within each frame and consistency across frames. 📜More👇

Gradio

19,986 次观看 • 2 年前

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

Anton Obukhov

39,295 次观看 • 1 年前

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

Alex Carlier

199,520 次观看 • 2 年前

xAI absolutely cooked with the new Grok Imagine model! The temporal consistency is rock-solid. The penguin's anatomy, lighting, and proportions stay locked in for the full 10 seconds with no weird morphing or melting. In less than 30 seconds, Grok created a video with snow spray building realistically, motion blur, and depth of field. The physics simulation rivals other top models.

xAI absolutely cooked with the new Grok Imagine model! The temporal consistency is rock-solid. The penguin's anatomy, lighting, and proportions stay locked in for the full 10 seconds with no weird morphing or melting. In less than 30 seconds, Grok created a video with snow spray building realistically, motion blur, and depth of field. The physics simulation rivals other top models.

tetsuo

76,456 次观看 • 4 个月前

Why is action chunking crucial for robot dexterity? 🤖 - We identify a natural tradeoff between temporal consistency and reactivity - New policy decoding technique that is *both* temporally consistent & fully reactive ICLR 2025 paper: A short thread 🧵

Why is action chunking crucial for robot dexterity? 🤖 - We identify a natural tradeoff between temporal consistency and reactivity - New policy decoding technique that is both temporally consistent & fully reactive ICLR 2025 paper: A short thread 🧵

Chelsea Finn

35,496 次观看 • 1 年前

The HTTP client CLI tool is now available in Homebrew, for free! To install it, launch the `brew install ijhttp` command in the terminal. 🧵 Check out the thread below for more details! 🧵

The HTTP client CLI tool is now available in Homebrew, for free! To install it, launch the `brew install ijhttp` command in the terminal. 🧵 Check out the thread below for more details! 🧵

IntelliJ IDEA, a JetBrains IDE

25,239 次观看 • 1 年前

Doesn't look like the super low-res depth maps from the iPhone Pro's LiDAR sensor would be too useful as supervision (or sanity check) for recent monocular depth estimators.

Doesn't look like the super low-res depth maps from the iPhone Pro's LiDAR sensor would be too useful as supervision (or sanity check) for recent monocular depth estimators.

Chris Offner

66,034 次观看 • 1 年前

Huge news! This is a major breakthrough in character consistency for AI videos. Kling AI released "Custom Models". You can now train your own video for superior character consistency. Let's take a look 🧵:

Huge news! This is a major breakthrough in character consistency for AI videos. Kling AI released "Custom Models". You can now train your own video for superior character consistency. Let's take a look 🧵:

Halim Alrasihi

207,391 次观看 • 1 年前

Discover what RPG delights await in Dragon Quest I & II HD-2D Remake. New in-depth overview video details enhancements and rebuilt features:

Discover what RPG delights await in Dragon Quest I & II HD-2D Remake. New in-depth overview video details enhancements and rebuilt features:

PlayStation

318,753 次观看 • 9 个月前

Check out the first teaser trailer for LiquiGen Immersion! All simmed in real-time & rendered with Path Tracer in UE. Join the waitlist for the most in-depth LiquiGen beginner course below - link in 🧵

Check out the first teaser trailer for LiquiGen Immersion! All simmed in real-time & rendered with Path Tracer in UE. Join the waitlist for the most in-depth LiquiGen beginner course below - link in 🧵

Jesse Pitela

20,801 次观看 • 1 年前

Our long-awaited Skate Core Update is now LIVE 🛹🔥 Peep all the changes in our dev blog → Don’t own Session yet? Fix that here →

Our long-awaited Skate Core Update is now LIVE 🛹🔥 Peep all the changes in our dev blog → Don’t own Session yet? Fix that here →

Session: Skate Sim

102,122 次观看 • 3 个月前

🛹 Introducing @TOUGHIESnft DRiP, by @AbbieSolana and faceless 🟡. Look out for redeemable Legendaries 👀

🛹 Introducing @TOUGHIESnft DRiP, by @AbbieSolana and faceless 🟡. Look out for redeemable Legendaries 👀

DRiP 💧

11,487 次观看 • 2 年前

Discover the right 3D Geometric Foundation Model for your task—whether it’s stereo matching, multi-view depth estimation, video depth, pose estimation, semantic understanding, or novel view synthesis. Explore more insights in our #E3DBench #FoundationModel #3D #GaussianSplatting. Project Webpage:

Discover the right 3D Geometric Foundation Model for your task—whether it’s stereo matching, multi-view depth estimation, video depth, pose estimation, semantic understanding, or novel view synthesis. Explore more insights in our #E3DBench #FoundationModel #3D #GaussianSplatting. Project Webpage:

Zhiwen(Aaron) Fan

29,920 次观看 • 1 年前

Trying out realtime video-to-depth on an iPhone 15 using Depth Anything V2.

Trying out realtime video-to-depth on an iPhone 15 using Depth Anything V2.

Tim Field

21,835 次观看 • 2 年前

Gave a robot 3D vision with just a regular camera👁️ Full Tutorial: Deployed #Depth Anything V3 on NVIDIA Robotics Jetson AGX Orin. It estimates depth from 2D images in real-time—no special sensors needed. Just need #Monocular depth estimation + #TensorRT optimization + #ROS2 integration. 👉 Learn more about reComputer Robotics J5011: #TheAIHardwarePartner

Gave a robot 3D vision with just a regular camera👁️ Full Tutorial: Deployed #Depth Anything V3 on NVIDIA Robotics Jetson AGX Orin. It estimates depth from 2D images in real-time—no special sensors needed. Just need #Monocular depth estimation + #TensorRT optimization + #ROS2 integration. 👉 Learn more about reComputer Robotics J5011: #TheAIHardwarePartner

Seeed Studio

16,966 次观看 • 3 个月前

❗New In-Depth Paper❗ Capping a two-year NATO SPS project, we are absolutely delighted to publish our report entitled "Primed for Deterrence? NATO and the Indo-Pacific in the Age of Great Power Competition". Read🔸 NATO

❗New In-Depth Paper❗ Capping a two-year NATO SPS project, we are absolutely delighted to publish our report entitled "Primed for Deterrence? NATO and the Indo-Pacific in the Age of Great Power Competition". Read🔸 NATO

CSDS

10,410 次观看 • 1 年前