SkalskiP's banner

SkalskiP

@skalskip92 • 47,631 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

1,473,978 просмотров

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

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

652,911 просмотров

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:

1,572,248 просмотров

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

708,147 просмотров

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

72,190 просмотров

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 просмотров

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:

79,277 просмотров

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

54,552 просмотров

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

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

592,161 просмотров

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:

504,759 просмотров

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:

121,367 просмотров

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 просмотров

"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:

197,880 просмотров

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

336,790 просмотров

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:

241,301 просмотров

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:

112,872 просмотров

upcoming basketball AI tutorial will be packed with strong visuals; can't wait to ship it

upcoming basketball AI tutorial will be packed with strong visuals; can't wait to ship it

72,304 просмотров

supervision-0.24.0 is out! you can finally count per-class line crossings. many of you have been asking for this, now we have it! it took me barely 30 minutes to make this demo using supervision! link:

supervision-0.24.0 is out! you can finally count per-class line crossings. many of you have been asking for this, now we have it! it took me barely 30 minutes to make this demo using supervision! link:

165,745 просмотров

it’s alive. finally trained my first SO-ARM101 policy. basic autonomous pick and place works. more complex stuff soon.

it’s alive. finally trained my first SO-ARM101 policy. basic autonomous pick and place works. more complex stuff soon.

49,734 просмотров

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

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:

885,813 просмотров • 1 месяц назад

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:

2,050,207 просмотров • 2 лет назад

manual data labeling is over

manual data labeling is over

295,331 просмотров • 8 месяцев назад

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:

329,670 просмотров • 11 месяцев назад

few weeks ago I gave a talk about computer vision and sports 45 minutes, but you can probably watch it at 2x speed over dinner link:

few weeks ago I gave a talk about computer vision and sports 45 minutes, but you can probably watch it at 2x speed over dinner link:

21,213 просмотров • 18 дней назад

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:

293,091 просмотров • 1 год назад

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:

427,286 просмотров • 1 год назад

true AGI check your split the G score haha with Roboflow

true AGI check your split the G score haha with Roboflow

303,581 просмотров • 1 год назад

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:

135,852 просмотров • 7 месяцев назад

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:

72,956 просмотров • 4 месяцев назад

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 ↓

399,903 просмотров • 2 лет назад

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 просмотров • 6 месяцев назад

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.

266,005 просмотров • 1 год назад

- 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

93,025 просмотров • 7 месяцев назад

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!

159,608 просмотров • 1 год назад

CVPR 2025 papers pt. 1 - Gaze-LLE Gaze-LLE simplifies gaze target estimation by building on top of a frozen DINOv2 visual foundation model; SOTA performance; open source code and model more papers: ↓ more

Sensitive content

This media may contain sensitive content.

CVPR 2025 papers pt. 1 - Gaze-LLE Gaze-LLE simplifies gaze target estimation by building on top of a frozen DINOv2 visual foundation model; SOTA performance; open source code and model more papers: ↓ more

96,057 просмотров • 1 год назад

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 просмотров • 2 лет назад

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 просмотров • 1 год назад

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:

188,590 просмотров • 2 лет назад

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0

124,358 просмотров • 1 год назад