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。

How can we use test-time compute for spatial understanding? 🤔 In InterPose, we propose to repeatedly sample generative video models to help two-view pose estimation and reconstruction, by leveraging the video models' keyframe interpolation abilities. A 🧵... (1/8)

Ricardo Martin-Brualla

3,272 subscribers

21,685 次观看 • 1 年前 •via X (Twitter)

科学技术艺术教育

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

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,801 次观看 • 1 年前

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇

Gradio

93,074 次观看 • 2 年前

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

67,135 次观看 • 3 个月前

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

Learn how to combine a deep learning model for pose estimation to perform a 3D reconstruction using two cameras 📸

Learn how to combine a deep learning model for pose estimation to perform a 3D reconstruction using two cameras 📸

MATLAB

15,665 次观看 • 1 年前

supervision-0.26.0 is out we finally released support for ViTPose and ViTPose++ pose estimation models from Hugging Face transformers link:

supervision-0.26.0 is out we finally released support for ViTPose and ViTPose++ pose estimation models from Hugging Face transformers link:

SkalskiP

112,872 次观看 • 10 个月前

Diffusion models have amazing image creation abilities. But how well does their generative knowledge transfer to discriminative tasks? We present Diffusion Classifier: strong classification results with pretrained conditional diffusion models, *with no additional training*! 1/9

Diffusion models have amazing image creation abilities. But how well does their generative knowledge transfer to discriminative tasks? We present Diffusion Classifier: strong classification results with pretrained conditional diffusion models, with no additional training! 1/9

Alex Li

95,304 次观看 • 2 年前

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

Hong-Xing (Koven) Yu

66,615 次观看 • 1 年前

I always thought camera pose estimation is necessary for 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and novel view rendering out. Key technique: spatial memory network from Spann3R and Gaussian head supervised by pointmap loss plus photometric loss. See more at:

I always thought camera pose estimation is necessary for 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and novel view rendering out. Key technique: spatial memory network from Spann3R and Gaussian head supervised by pointmap loss plus photometric loss. See more at:

Heng Yang

20,160 次观看 • 1 年前

Can we use motion to prompt diffusion models? Our #ICLR2024 paper does just that. We propose Motion Guidance, a technique that allows users to edit an image by specifying “where things should move.”

Can we use motion to prompt diffusion models? Our #ICLR2024 paper does just that. We propose Motion Guidance, a technique that allows users to edit an image by specifying “where things should move.”

Daniel Geng

16,304 次观看 • 2 年前

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

Hao AI Lab

78,660 次观看 • 10 个月前

AI’s next frontier is Spatial Intelligence, a technology that will turn seeing into reasoning, perception into action, and imagination into creation. But what is it? Why does it matter? How do we build it? And how can we use it? Today, I want to share with you my thoughts on building and using world models to unlock spatial intelligence in this essay below. 1/n

AI’s next frontier is Spatial Intelligence, a technology that will turn seeing into reasoning, perception into action, and imagination into creation. But what is it? Why does it matter? How do we build it? And how can we use it? Today, I want to share with you my thoughts on building and using world models to unlock spatial intelligence in this essay below. 1/n

Fei-Fei Li

925,421 次观看 • 6 个月前

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

MrNeRF

24,580 次观看 • 10 个月前

🚨New paper! Generative models are often “miscalibrated”. We calibrate diffusion models, LLMs, and more to meet desired distributional properties. E.g. we finetune protein models to better match the diversity of natural proteins.

🚨New paper! Generative models are often “miscalibrated”. We calibrate diffusion models, LLMs, and more to meet desired distributional properties. E.g. we finetune protein models to better match the diversity of natural proteins.

Brian L Trippe

20,409 次观看 • 7 个月前

🤔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

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

(1/3) Can we turn text-to-image models into photorealistic 3D generators? ViewDiff (#CVPR2024) produces realistic, multi-view consistent images of real-world 3D objects in authentic surroundings. Website Video How does it work?

(1/3) Can we turn text-to-image models into photorealistic 3D generators? ViewDiff (#CVPR2024) produces realistic, multi-view consistent images of real-world 3D objects in authentic surroundings. Website Video How does it work?

Matthias Niessner

34,749 次观看 • 2 年前

Do 3D reconstruction transformers really need a billion parameters, or are most of those layers just doing the same thing over and over? Introducing Déjà View: a single transformer block, looped K times, that matches or beats models 8–10× its size with lower compute. 🧵

Do 3D reconstruction transformers really need a billion parameters, or are most of those layers just doing the same thing over and over? Introducing Déjà View: a single transformer block, looped K times, that matches or beats models 8–10× its size with lower compute. 🧵

Tobias Fischer

90,634 次观看 • 8 天前

Sometimes I generate a video like this, and I pause for a second to realize how far we have come with AI video models. This one is Kling 2.5, 1080p. You can find the prompt below 👇

Sometimes I generate a video like this, and I pause for a second to realize how far we have come with AI video models. This one is Kling 2.5, 1080p. You can find the prompt below 👇

Alex Patrascu

51,097 次观看 • 7 个月前