Loading video...

Video Failed to Load

Go Home

Left: raw depth from the OAK-D Pro W camera Right: depth from FoundationStereo

YuXiang_IRVL's profile picture

Yu Xiang

5,979 subscribers

32,598 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Raised from the depth WIP
0:12

Raised from the depth WIP

indifference

31,201 views • 6 months ago

Let me share how the maps look like. Normal was estimated from the source image with StableNormal ( and Refined Depth came from promptDA ( + Lidar Depth. If you pause the video, you will see the differences in depths.
0:12

Let me share how the maps look like. Normal was estimated from the source image with StableNormal ( and Refined Depth came from promptDA ( + Lidar Depth. If you pause the video, you will see the differences in depths.

Chris make some 3D scans

44,280 views • 1 year ago

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.
0:13

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 views • 1 year ago

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
0:18

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 views • 4 months ago

Xavier Watts single high, diagnoses the reverse, and closes. Made plays like this from depth all night
0:16

Xavier Watts single high, diagnoses the reverse, and closes. Made plays like this from depth all night

Billy M

75,465 views • 1 year ago

I'll always root for a team that open-sources its best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyant
0:10

I'll always root for a team that open-sources its best work, and Robbyant just did it properly. Robbyant, Ant Group's embodied-AI company, released LingBot-Vision, a vision foundation model for robots, and the part I love is the data. They trained it on 161M images, filtered down from 2B raw ones and mostly pulled straight from the open web, with no human labels, no edge detectors, no depth sensors anywhere in the loop. It learns the exact edges of objects from raw pixels. That's roughly a tenth of the data DINOv3 saw, and under a third of the training. And it shows in the results. On depth, working out how far away things are, the 1B model edges out a 7B on NYU-Depth. It also powers LingBot-Depth 2.0, which reads the surfaces cameras usually choke on, glass and mirrors, and halves indoor depth error. LingBot-Vision is fully open. Weights from the 1.1B flagship down to a tiny 21M version, code, and the paper. This is the timeline I want more of. Robbyant

Chubby♨️

48,249 views • 9 days ago

Quick look at Nathan Anderson (‘24, IL) has come out working the mid-80s on the FB from the left side & higher slot. Mid-70s SL in the mix as well. Showed a CH in the mix as well w/good depth to it. Perfect Game Illinois PG_Uncommitted #WWBAWorlds
0:12

Quick look at Nathan Anderson (‘24, IL) has come out working the mid-80s on the FB from the left side & higher slot. Mid-70s SL in the mix as well. Showed a CH in the mix as well w/good depth to it. Perfect Game Illinois PG_Uncommitted #WWBAWorlds

Perfect Game Scout

13,132 views • 2 years ago

‘26 Braydon McKendrick (IL) Logan Vols Baseball recruit FB: 85-88 CB: 75-78 (2400+ depth) CH: 81-83 (1400s) Uptempo, aggressive look from the 5’11” 190-pounder who challenged hitters right from the jump. Feel for 3 from higher 3/4 slot. Prep Baseball Illinois
0:12

‘26 Braydon McKendrick (IL) Logan Vols Baseball recruit FB: 85-88 CB: 75-78 (2400+ depth) CH: 81-83 (1400s) Uptempo, aggressive look from the 5’11” 190-pounder who challenged hitters right from the jump. Feel for 3 from higher 3/4 slot. Prep Baseball Illinois

Shooter Hunt

16,510 views • 4 months ago

I found a new source of joy. This new depth lock screen app comes from AppsLab
0:13

I found a new source of joy. This new depth lock screen app comes from AppsLab

Ice Universe

45,704 views • 2 months ago

Matthew Manis ('26, TX) working 88-91 mph on the FB. Commanding well w/ spin above 2300 RPMs. Flashed a SW 76-79 mph w/ spin above 2600 RPMs. Showing good depth. CB 75-76 w/ bigger 1-7 shape & depth. #HookEm commit #PGNational Perfect Game Texas
0:17

Matthew Manis ('26, TX) working 88-91 mph on the FB. Commanding well w/ spin above 2300 RPMs. Flashed a SW 76-79 mph w/ spin above 2600 RPMs. Showing good depth. CB 75-76 w/ bigger 1-7 shape & depth. #HookEm commit #PGNational Perfect Game Texas

PG Showcases

11,135 views • 1 year ago

improving my 3D hand tracking template by adding depth-anything-v2 using mediapipe for X/Y movement and depth-anything for Z movement here i'm controlling a threejs scene in realtime with input from a single webcam
0:15

improving my 3D hand tracking template by adding depth-anything-v2 using mediapipe for X/Y movement and depth-anything for Z movement here i'm controlling a threejs scene in realtime with input from a single webcam

AA

28,276 views • 3 months ago

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).
0:15

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

Gábor Pribék

142,027 views • 2 months ago

D Fox Escape Might be Crucial 🙃📸. HOLD R2 IF IN YOUR RIGHT HAND FLICK RIGHT STICK FROM RIGHT TO LEFT AND VICE VERSA
0:12

D Fox Escape Might be Crucial 🙃📸. HOLD R2 IF IN YOUR RIGHT HAND FLICK RIGHT STICK FROM RIGHT TO LEFT AND VICE VERSA

MR-BOXDAT_TTV

81,129 views • 4 months ago

Yanking and pulling through a bar at rest from the ground builds more muscle than any other timid and controlled rep IMO Many love depth drops, because of that extremely short but extremely high exposure to forces A power row is the depth jump for the upper body/back
0:13

Yanking and pulling through a bar at rest from the ground builds more muscle than any other timid and controlled rep IMO Many love depth drops, because of that extremely short but extremely high exposure to forces A power row is the depth jump for the upper body/back

Official Strength Debates

45,694 views • 9 months ago

Over 3ft fresh snow depth as of now at Solang nallah in Kullu of Himachal Pradesh Video from Joni bhai
0:19

Over 3ft fresh snow depth as of now at Solang nallah in Kullu of Himachal Pradesh Video from Joni bhai

Weatherman Shubham

24,607 views • 1 year ago

With the world at your fingertips, what's everyone creating? Share some dope work in the comments. Last Dude on Earth Vlog | Sora 2 Pro Camera details: 35 mm lens | handheld | depth-of-field | cinematic grain | real-time exposure shifts | selfie vlog POV
0:15

With the world at your fingertips, what's everyone creating? Share some dope work in the comments. Last Dude on Earth Vlog | Sora 2 Pro Camera details: 35 mm lens | handheld | depth-of-field | cinematic grain | real-time exposure shifts | selfie vlog POV

Dave Clark

11,816 views • 9 months ago

Spencer Krasner ('26, FL) working 88-90 mph on the FB, showing some life to it. Flashed a SL 77-78 mph w/ good shape & 10-4 depth. Flashed a CH 81-82 mph w/ good feel to kill spin & show depth. #Gamecocks commit #PGNational Perfect Game Florida
0:16

Spencer Krasner ('26, FL) working 88-90 mph on the FB, showing some life to it. Flashed a SL 77-78 mph w/ good shape & 10-4 depth. Flashed a CH 81-82 mph w/ good feel to kill spin & show depth. #Gamecocks commit #PGNational Perfect Game Florida

PG Showcases

19,723 views • 1 year ago

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:
0:14

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

30,010 views • 1 year ago