Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

2,889 subscribers

52,234 Aufrufe • vor 3 Jahren •via X (Twitter)

Nachrichten & Politik Wissenschaft & Technologie Bildung #CVPR2023

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von AntiFisherYu001

AntiFisherYu001vor 2 Jahren

You are a murderer

Profilbild von Adrian

Adrianvor 3 Jahren

@ValueAnalyst1 @a_meta4 check it out

Profilbild von MinotaurOnLucy

MinotaurOnLucyvor 3 Jahren

As an outsider, I have the following questions: What is the current state-of-the-art performance for out of distribution cases? If it is not good, will we see a foundational model that achieves good out of distribution performance in the near term, or would it be more mid term?

Profilbild von julien michot

julien michotvor 3 Jahren

Why "impossible"? Here you get the most plausible depths.

Profilbild von Nikolaos Sarafianos

Nikolaos Sarafianosvor 3 Jahren

This is great work! Did you test it on humans at various distances from the camera by any chance?

Profilbild von Fisher Yu

Fisher Yuvor 3 Jahren

We test the method on street scenes that have people. However, it is indeed interesting to see whether we can use the method to estimate depth in human-centric scenes.

Profilbild von ζ Pedram ζ

ζ Pedram ζvor 3 Jahren

Neat idea, github?

Profilbild von Fisher Yu

Fisher Yuvor 3 Jahren

github link: The full code will be released before CVPR 2023.

Profilbild von test bot

test botvor 3 Jahren

@Scobleizer 69

Profilbild von 𝘃𝗿𝗹𝗹𝗿𝘃

𝘃𝗿𝗹𝗹𝗿𝘃vor 3 Jahren

@Scobleizer Great work!

Ähnliche Videos

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 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 2 Jahren

After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 reveals two key insights: 💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture. ✨ A single depth-ray representation is enough. No complex 3D tasks. Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series. The core team members, aside from me: Haotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen. 👇(1/n) #DepthAnything3

After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 reveals two key insights: 💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture. ✨ A single depth-ray representation is enough. No complex 3D tasks. Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series. The core team members, aside from me: Haotong Lin, Sili Chen, Jun Hao Liew, Donny Y. Chen. 👇(1/n) #DepthAnything3

Bingyi Kang

514,365 Aufrufe • vor 7 Monaten

Want to use Depth Anything, but need metric depth rather than relative depth? Thrilled to introduce Prompt Depth Anything, a new paradigm for accurate metric depth estimation with up to 4K resolution. 👉Key Message: Depth foundation models like DA have already internalized rich geometric knowledge of the 3D world but lack a proper way to elicit it. Inspired by the success of prompting in LLMs, we propose prompting Depth Anything with metric cues to produce metric depth. This method proves to be very effective when using a low-cost lidar (e.g., iPhone's LiDAR), which is widely available, as prompts. We believe the prompt can generalize to other forms as long as scale information is provided. Prompt Depth Anything offers 1⃣A series of models for iPhone lidars. 2⃣4D reconstruction from monocular videos (captured with iPhone). 3⃣Improved generalization ability for robot manipulation, e.g. Training on cans but generalizing on glasses. 4⃣More detailed depth annotations for the ScanNet++ dataset. The first author is our excellent intern Haotong Lin. Paper: Huggingface: Project Page: Code:

Want to use Depth Anything, but need metric depth rather than relative depth? Thrilled to introduce Prompt Depth Anything, a new paradigm for accurate metric depth estimation with up to 4K resolution. 👉Key Message: Depth foundation models like DA have already internalized rich geometric knowledge of the 3D world but lack a proper way to elicit it. Inspired by the success of prompting in LLMs, we propose prompting Depth Anything with metric cues to produce metric depth. This method proves to be very effective when using a low-cost lidar (e.g., iPhone's LiDAR), which is widely available, as prompts. We believe the prompt can generalize to other forms as long as scale information is provided. Prompt Depth Anything offers 1⃣A series of models for iPhone lidars. 2⃣4D reconstruction from monocular videos (captured with iPhone). 3⃣Improved generalization ability for robot manipulation, e.g. Training on cans but generalizing on glasses. 4⃣More detailed depth annotations for the ScanNet++ dataset. The first author is our excellent intern Haotong Lin. Paper: Huggingface: Project Page: Code:

Bingyi Kang

67,550 Aufrufe • vor 1 Jahr

The iPhone LiDAR depth is pretty stable but low-res and low detail. Monodepth is highly detailed but unstable ("depth flickering"). For more stable and detailed metric depth, I solve for the per-frame affine transform that optimally "anchors" the monodepth to the LiDAR.

The iPhone LiDAR depth is pretty stable but low-res and low detail. Monodepth is highly detailed but unstable ("depth flickering"). For more stable and detailed metric depth, I solve for the per-frame affine transform that optimally "anchors" the monodepth to the LiDAR.

Chris Offner

43,116 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

Excited to share our work InfiniDepth (CVPR 2026) — casting monocular depth estimation as a neural implicit field, which enables: 🔍 Arbitrary-Resolution 📐 Accurate Metric Depth 📷 Large-View Novel View Synthesis Feel free to try our code:

Excited to share our work InfiniDepth (CVPR 2026) — casting monocular depth estimation as a neural implicit field, which enables: 🔍 Arbitrary-Resolution 📐 Accurate Metric Depth 📷 Large-View Novel View Synthesis Feel free to try our code:

Sida Peng

38,675 Aufrufe • vor 2 Monaten

"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 Aufrufe • vor 3 Monaten

AnyDepth Depth Estimation Made Easy

AnyDepth Depth Estimation Made Easy

AK

14,765 Aufrufe • vor 5 Monaten

Grab your snorkel and hold your breath because it’s about to get deep with Cryptic Depth washing up on the Rift for the first time November 9th UTC. 🌊🧜 Cryptic Depth Miss Fortune 🌊🧜 Cryptic Depth Morgana 🌊🧜 Cryptic Depth Thresh 🌊🧜 Cryptic Depth Kayle 🌊🧜 Cryptic Depth Pantheon

Grab your snorkel and hold your breath because it’s about to get deep with Cryptic Depth washing up on the Rift for the first time November 9th UTC. 🌊🧜 Cryptic Depth Miss Fortune 🌊🧜 Cryptic Depth Morgana 🌊🧜 Cryptic Depth Thresh 🌊🧜 Cryptic Depth Kayle 🌊🧜 Cryptic Depth Pantheon

League of Legends: Wild Rift

300,378 Aufrufe • vor 7 Monaten

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 Aufrufe • vor 1 Monat

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 Aufrufe • vor 2 Jahren

Image to depth using Marigold and ConfyUI Then depth to 3D geometry in Blender Super interesting stuff 🤯

Image to depth using Marigold and ConfyUI Then depth to 3D geometry in Blender Super interesting stuff 🤯

A.I.Warper

201,906 Aufrufe • vor 2 Jahren

InfiniDepth: Fine-grained depth estimation at any resolution; models depth as a neural implicit field instead of a grid; - tops DepthAnything; - recovers sharp details w/ a lightweight 15M decoder.

InfiniDepth: Fine-grained depth estimation at any resolution; models depth as a neural implicit field instead of a grid; - tops DepthAnything; - recovers sharp details w/ a lightweight 15M decoder.

Wildminder

59,147 Aufrufe • vor 5 Monaten

DVD Deterministic Video Depth Estimation with Generative Priors paper:

DVD Deterministic Video Depth Estimation with Generative Priors paper:

AK

62,042 Aufrufe • vor 3 Monaten

"It's one thing to have depth on paper, to have depth in your capacity, but you gotta tap into it." Stu Grimson breaks down Edmonton and Dallas' forward groups. Erika Wachter Barnes | #LetsGoOilers | #TexasHockey | #StanleyCup

"It's one thing to have depth on paper, to have depth in your capacity, but you gotta tap into it." Stu Grimson breaks down Edmonton and Dallas' forward groups. Erika Wachter Barnes | #LetsGoOilers | #TexasHockey | #StanleyCup

NHL Media

43,416 Aufrufe • vor 1 Jahr

The superpower of this group was our connectivity and depth.

The superpower of this group was our connectivity and depth.

Detroit Pistons

16,303 Aufrufe • vor 29 Tagen

working on more depth w lower weights after a couple weeks off from back squatting.

working on more depth w lower weights after a couple weeks off from back squatting.

hasanbabi

189,812 Aufrufe • vor 3 Jahren

Checkout our YouTube Channel for the entire video! We go more into depth on our #2024lifestylewrap

Sensitive content

Checkout our YouTube Channel for the entire video! We go more into depth on our #2024lifestylewrap

Theimpulsiveduo

33,066 Aufrufe • vor 1 Jahr