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。

DVD Deterministic Video Depth Estimation with Generative Priors paper:

AK

502,512 subscribers

62,042 次观看 • 3 个月前 •via X (Twitter)

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

Learning Temporally Consistent Video Depth from Video Diffusion Priors This work addresses the challenge of video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. Instead of directly

Learning Temporally Consistent Video Depth from Video Diffusion Priors This work addresses the challenge of video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. Instead of directly

AK

81,634 次观看 • 2 年前

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

"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 次观看 • 2 个月前

TikTok presents Depth Anything Unleashing the Power of Large-Scale Unlabeled Data paper page: demo: Depth Anything is trained on 1.5M labeled images and 62M+ unlabeled images jointly, providing the most capable Monocular Depth Estimation (MDE) foundation models with the following features: zero-shot relative depth estimation, better than MiDaS v3.1 (BEiTL-512) zero-shot metric depth estimation, better than ZoeDepth optimal in-domain fine-tuning and evaluation on NYUv2 and KITTI

TikTok presents Depth Anything Unleashing the Power of Large-Scale Unlabeled Data paper page: demo: Depth Anything is trained on 1.5M labeled images and 62M+ unlabeled images jointly, providing the most capable Monocular Depth Estimation (MDE) foundation models with the following features: zero-shot relative depth estimation, better than MiDaS v3.1 (BEiTL-512) zero-shot metric depth estimation, better than ZoeDepth optimal in-domain fine-tuning and evaluation on NYUv2 and KITTI

AK

600,018 次观看 • 2 年前

Tencent just dropped GeometryCrafter on Hugging Face Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

Tencent just dropped GeometryCrafter on Hugging Face Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

AK

55,079 次观看 • 1 年前

AnyDepth Depth Estimation Made Easy

AnyDepth Depth Estimation Made Easy

AK

14,765 次观看 • 5 个月前

How can lightweight drones without depth cameras navigate using monocular images? Check out our paper at ISER 2023! MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction arXiv: website: Work led by Nate Simon

How can lightweight drones without depth cameras navigate using monocular images? Check out our paper at ISER 2023! MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction arXiv: website: Work led by Nate Simon

Anirudha Majumdar

27,642 次观看 • 2 年前

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.

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 次观看 • 1 年前

Generative World Renderer paper:

Generative World Renderer paper:

AK

14,238 次观看 • 2 个月前

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:

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 次观看 • 1 年前

Took it further with Omma, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Took it further with Omma, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

146,914 次观看 • 1 个月前

Early test run with freshly added depth estimation — Mixed Reality + Diffusion prototype to explore concepts, styles, and moods. #MixedReality #MR #AI #StableDiffusion #Quest3

Early test run with freshly added depth estimation — Mixed Reality + Diffusion prototype to explore concepts, styles, and moods. #MixedReality #MR #AI #StableDiffusion #Quest3

Hugues Bruyère

13,054 次观看 • 1 年前

🔥Diffusion Masters Transparent Objects in Videos! We introduce #DKT, a foundation model that repurposes video diffusion for zero-shot depth and normal estimation on Transparent and Reflective Objects with Superior Temporal Consistency Demo: Code:

🔥Diffusion Masters Transparent Objects in Videos! We introduce #DKT, a foundation model that repurposes video diffusion for zero-shot depth and normal estimation on Transparent and Reflective Objects with Superior Temporal Consistency Demo: Code:

Chongjie(CJ) Ye

27,942 次观看 • 5 个月前

Municipales 2026 à Mulhouse: Michèle Lutz (DVD) en tête avec 17,60% (estimation Elabe-Berger Levrault)

Municipales 2026 à Mulhouse: Michèle Lutz (DVD) en tête avec 17,60% (estimation Elabe-Berger Levrault)

BFM

44,007 次观看 • 3 个月前

Paper depth effect in Photoshop (_madebygray)

Paper depth effect in Photoshop (_madebygray)

Dr Fonts©

62,775 次观看 • 9 个月前

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

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 次观看 • 9 个月前

Monocular depth estimation is “impossible” because one image can’t measure depth geometrically. Our iDisc #CVPR2023 can group pixels w/o supervision and learn depth inductive bias on groups. We get LiDAR-like (but denser) depth from single images! More:

Monocular depth estimation is “impossible” because one image can’t measure depth geometrically. Our iDisc #CVPR2023 can group pixels w/o supervision and learn depth inductive bias on groups. We get LiDAR-like (but denser) depth from single images! More:

Fisher Yu

52,234 次观看 • 3 年前

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!

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

56,923 次观看 • 1 年前

Happy to share our new work, MVInverse, a feedforward framework for multiview PBR material estimation at ~10 fps. Multiview ViT (like VGGT, Pi3) can also do material estimation! Paper: Homepage: Code:

Happy to share our new work, MVInverse, a feedforward framework for multiview PBR material estimation at ~10 fps. Multiview ViT (like VGGT, Pi3) can also do material estimation! Paper: Homepage: Code:

Yuan Liu

11,933 次观看 • 5 个月前

Glad that our work “Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling”, led by Han Qi, has been accepted to IEEE Robotics and Automation Letters! 🎉 We propose Generative Predictive Control (GPC): sample action proposals from a pretrained diffusion policy (“look back”), roll them out with a diffusion-based action-conditioned video world model (“look forward”), then rank or optimize the actions using either a learned reward model or VLM preferences. Conceptually, this is trajectory optimization / MPC with hybrid sampling + gradient optimization, interpreted through modern diffusion priors and video world models. Interestingly, we first posted the paper on arXiv in Feb 2025, when action-conditioned video world models for planning were still rare—now this direction is rapidly gaining traction. Still many open questions, e.g., • how to avoid local minima in planning • what representations work best for world models • how to balance physics priors vs. data-driven learning Paper:

Glad that our work “Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling”, led by Han Qi, has been accepted to IEEE Robotics and Automation Letters! 🎉 We propose Generative Predictive Control (GPC): sample action proposals from a pretrained diffusion policy (“look back”), roll them out with a diffusion-based action-conditioned video world model (“look forward”), then rank or optimize the actions using either a learned reward model or VLM preferences. Conceptually, this is trajectory optimization / MPC with hybrid sampling + gradient optimization, interpreted through modern diffusion priors and video world models. Interestingly, we first posted the paper on arXiv in Feb 2025, when action-conditioned video world models for planning were still rare—now this direction is rapidly gaining traction. Still many open questions, e.g., • how to avoid local minima in planning • what representations work best for world models • how to balance physics priors vs. data-driven learning Paper:

Heng Yang

18,968 次观看 • 3 个月前