SkalskiP's banner

SkalskiP

@skalskip92 • 50,567 subscribers

Open-source Lead @roboflow. VLMs. GPU poor. Dog person. Coffee addict. Dyslexic. | GH: https://t.co/dEmzMDGXVf | HF: https://t.co/4Lx1Yw3CLF

Shorts

there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in crazy complex scenes like basketball probably my favorite computer vision model ever

there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in crazy complex scenes like basketball probably my favorite computer vision model ever

1,479,527 次观看

looks like we are working on the same thing haha; more soon

looks like we are working on the same thing haha; more soon

654,064 次观看

basketball AI (95% local AI + 5% GPT-6 Astra) - detect ball and players - track players - re-identify players across plays - OCR player numbers - recognize player in possession - detect court keypoints - map player positions and trajectories Astra is powerful, but expensive tool. use it when it actually makes a difference. ↓ deep dive

basketball AI (95% local AI + 5% GPT-6 Astra) - detect ball and players - track players - re-identify players across plays - OCR player numbers - recognize player in possession - detect court keypoints - map player positions and trajectories Astra is powerful, but expensive tool. use it when it actually makes a difference. ↓ deep dive

164,129 次观看

I can finally map NBA player's position from the camera perspective onto the court map it's still a bit shaky... I'll smooth it out later it's time to detect shooting motions and mark the shot location! some of the code has already been migrated to:

I can finally map NBA player's position from the camera perspective onto the court map it's still a bit shaky... I'll smooth it out later it's time to detect shooting motions and mark the shot location! some of the code has already been migrated to:

1,573,009 次观看

SAM3 video tracking is so good yesterday: collect data, train custom object detector, use tracker to estimate object motion - days today: track anything with text prompt - seconds

SAM3 video tracking is so good yesterday: collect data, train custom object detector, use tracker to estimate object motion - days today: track anything with text prompt - seconds

709,076 次观看

I spend a lot of time finding out what VLMs still can't do pretty excited to help change that we launched Roboflow Labs at Roboflow training data, evals and environments for real-world tasks. vision, multimodal reasoning, robotics and coding. link:

I spend a lot of time finding out what VLMs still can't do pretty excited to help change that we launched Roboflow Labs at Roboflow training data, evals and environments for real-world tasks. vision, multimodal reasoning, robotics and coding. link:

28,749 次观看

I used to hate working on projects like this... crazy how the word has changed over the past year; labeling is dead!

I used to hate working on projects like this... crazy how the word has changed over the past year; labeling is dead!

810,780 次观看

this might be the coolest-looking football AI visualization I ever created

this might be the coolest-looking football AI visualization I ever created

592,248 次观看

supervision - a computer vision library I created - just crossed 15,000 stars on GitHub! BBBRRRRRR! link:

supervision - a computer vision library I created - just crossed 15,000 stars on GitHub! BBBRRRRRR! link:

505,018 次观看

I'm starting to get more and more serious with YOLO-World; trying to solve real-life problems. I wanted to see if YOLO-World could recognize that the holes had been filled out. It was pretty tricky, but I learned a little about prompting. ↓ read more

I'm starting to get more and more serious with YOLO-World; trying to solve real-life problems. I wanted to see if YOLO-World could recognize that the holes had been filled out. It was pretty tricky, but I learned a little about prompting. ↓ read more

445,915 次观看

RF-DETR is now available in Hugging Face transformers state of the art in both detection and segmentation, outperforming YOLO architectures - checkpoints: - demo: - docs:

RF-DETR is now available in Hugging Face transformers state of the art in both detection and segmentation, outperforming YOLO architectures - checkpoints: - demo: - docs:

80,579 次观看

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

73,176 次观看

pip install trackers trackers v2.1.0 is out; this release adds support for ByteTrack, a fast tracking by detection algorithm focused on stable identities under occlusion. link:

pip install trackers trackers v2.1.0 is out; this release adds support for ByteTrack, a fast tracking by detection algorithm focused on stable identities under occlusion. link:

121,454 次观看

I'm taking my football/soccer project to the next level today, I worked on detecting players, referees, and the ball and mapping their positions from video frames to positions on the field. ↓ read more

I'm taking my football/soccer project to the next level today, I worked on detecting players, referees, and the ball and mapping their positions from video frames to positions on the field. ↓ read more

336,832 次观看

"can you do the same thing for football?" - I got this question 100x today yep, I actually did this last year - player detection and tracking - team clustering - perspective transformation end-to-end YT tutorial:

"can you do the same thing for football?" - I got this question 100x today yep, I actually did this last year - player detection and tracking - team clustering - perspective transformation end-to-end YT tutorial:

198,317 次观看

INSID3 segments objects across domains using ONLY ONE annotated example it works entirely without a segmentation decoder, task-specific fine-tuning, or external mask generators like SAM CVPR 2026 paper with enormous practical potential

INSID3 segments objects across domains using ONLY ONE annotated example it works entirely without a segmentation decoder, task-specific fine-tuning, or external mask generators like SAM CVPR 2026 paper with enormous practical potential

55,564 次观看

almost fully functional version of my football AI project today, I added player tracking using ByteTrack and projection of players onto the map code coming soon:

almost fully functional version of my football AI project today, I added player tracking using ByteTrack and projection of players onto the map code coming soon:

241,328 次观看

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:

113,232 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

data labeling is dead GPT-6 Astra easily tells Celtics players from Knicks players whether they play at home or on the road

data labeling is dead GPT-6 Astra easily tells Celtics players from Knicks players whether they play at home or on the road

685,694 次观看 • 1 个月前

supervision just hit 40,000 GitHub stars! it now powers over 6.5k open-source computer vision projects, including all my demos like basketball AI link:

supervision just hit 40,000 GitHub stars! it now powers over 6.5k open-source computer vision projects, including all my demos like basketball AI link:

890,558 次观看 • 4 个月前

football AI code is finally open-source - player detection and tracking - team clustering - camera calibration I still need to work on README; don't judge me on that code:

football AI code is finally open-source - player detection and tracking - team clustering - camera calibration I still need to work on README; don't judge me on that code:

2,089,408 次观看 • 2 年前

McByte shipped in trackers 2.6.0 similar to ByteTrack, but association is guided by segmentation masks (SAM + Cutie), not just boxes when players overlap and box IoU gets ambiguous, masks settle who is who here it is side by side with OC-SORT link:

McByte shipped in trackers 2.6.0 similar to ByteTrack, but association is guided by segmentation masks (SAM + Cutie), not just boxes when players overlap and box IoU gets ambiguous, masks settle who is who here it is side by side with OC-SORT link:

122,027 次观看 • 2 个月前

is Astra really this good at VLA? I spent hours trying a zero-shot demo with the SO-101 arm and this is all I got

is Astra really this good at VLA? I spent hours trying a zero-shot demo with the SO-101 arm and this is all I got

45,756 次观看 • 1 个月前

manual data labeling is over

manual data labeling is over

295,331 次观看 • 11 个月前

supervision, the open-source library I created 2 years ago, is crossing 30,000 stars on GitHub! thank you to everyone who helped me build this project! it took us 4,000+ commits, 1,000+ PRs and 100+ contributors to do it. link:

supervision, the open-source library I created 2 years ago, is crossing 30,000 stars on GitHub! thank you to everyone who helped me build this project! it took us 4,000+ commits, 1,000+ PRs and 100+ contributors to do it. link:

329,765 次观看 • 1 年前

supervision, the open-source library I created a year ago, has crossed 20,000 stars on GitHub this weekend! thank you to everyone who helped me build this project! it took us 3,500+ commits, 850+ PRs and 80+ contributors to do it. repository:

supervision, the open-source library I created a year ago, has crossed 20,000 stars on GitHub this weekend! thank you to everyone who helped me build this project! it took us 3,500+ commits, 850+ PRs and 80+ contributors to do it. repository:

427,526 次观看 • 2 年前

I'm experimenting with using SAM2 for automatic tracking of NBA players; it's mind-blowing how well this model performs out of the box. we might even add a SAM2-based tracker to the trackers package at some point. trackers:

I'm experimenting with using SAM2 for automatic tracking of NBA players; it's mind-blowing how well this model performs out of the box. we might even add a SAM2-based tracker to the trackers package at some point. trackers:

293,362 次观看 • 1 年前

true AGI check your split the G score haha with Roboflow

true AGI check your split the G score haha with Roboflow

303,581 次观看 • 1 年前

here is the final version of my vehicle speed estimation demo read the thread below to learn how I built it. I will cover: - detection - tracking - perspective transformation - speed calculation - some bonus ideas ↓

here is the final version of my vehicle speed estimation demo read the thread below to learn how I built it. I will cover: - detection - tracking - perspective transformation - speed calculation - some bonus ideas ↓

399,990 次观看 • 2 年前

data labeling is dead. long live distillation. from data to object detection endpoint in 90 seconds. link:

data labeling is dead. long live distillation. from data to object detection endpoint in 90 seconds. link:

136,190 次观看 • 10 个月前

FLUX inpainting I know I'm late to the FLUX party, but I hope it's still okey if I drop something cool.

FLUX inpainting I know I'm late to the FLUX party, but I hope it's still okey if I drop something cool.

266,093 次观看 • 2 年前

check out my mini terminator spent some time over the last few days teaching my reachy mini to follow a face; there is still room for improvement, especially in the tracking algo

check out my mini terminator spent some time over the last few days teaching my reachy mini to follow a face; there is still room for improvement, especially in the tracking algo

100,536 次观看 • 9 个月前

been a minute since I worked with soccer, but trackers-2.3.0 dropped and I had to try OC-SORT it's built for scenes where objects constantly occlude each other, exactly what happens on a soccer pitch. ran it on SoccerNet. looks great. link:

been a minute since I worked with soccer, but trackers-2.3.0 dropped and I had to try OC-SORT it's built for scenes where objects constantly occlude each other, exactly what happens on a soccer pitch. ran it on SoccerNet. looks great. link:

73,258 次观看 • 7 个月前

- if SAM3 is so good, do we still need other models? - yes. SAM3 is too large for low compute edge devices and too slow for real-time use. we still need light and fast models for edge workloads. distill SAM3 into smaller model and deploy it in seconds with Roboflow rapid

- if SAM3 is so good, do we still need other models? - yes. SAM3 is too large for low compute edge devices and too slow for real-time use. we still need light and fast models for edge workloads. distill SAM3 into smaller model and deploy it in seconds with Roboflow rapid

94,280 次观看 • 11 个月前

this guy took my Football AI project and used it to build a 3D representation of the game; CRAAAAAZY!

this guy took my Football AI project and used it to build a 3D representation of the game; CRAAAAAZY!

159,722 次观看 • 1 年前

lots of you asked if soccer AI can detect the ball; I just added this functionality code:

lots of you asked if soccer AI can detect the ball; I just added this functionality code:

152,451 次观看 • 2 年前

Automated NBA match commentary using OpenAI vision and TTS (with code!) Everyone is bragging about projects that generate automatic video commentary, but no one is showing the code. I did it while waiting for the plane. code:

Automated NBA match commentary using OpenAI vision and TTS (with code!) Everyone is bragging about projects that generate automatic video commentary, but no one is showing the code. I did it while waiting for the plane. code:

188,624 次观看 • 2 年前

this is how you annotate data in 2025 (I've been told this egg demo may trigger some US people)

this is how you annotate data in 2025 (I've been told this egg demo may trigger some US people)

107,465 次观看 • 1 年前