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。

more magic/AI mesh selection, this one w/ SAM2 which takes an initial box/points instead of a text prompt. SAM2 is much faster, in 'stream' mode I can send it frames like it's processing a video (this capture is 1x, SAM2 running locally on 8GB 3070ti).

Ryan Schmidt

7,929 subscribers

21,203 次观看 • 1 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

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:

SkalskiP @ CVPR2026

292,965 次观看 • 1 年前

Super excited to introduce SAM2 Studio! 🚀🤖 I've been getting a lot of questions lately on supporting AI inference tailored for patient data and sensitive workflows. We optimized SAM2 to run completely on-device in real time for all of your medical segmentation workflows - including surgical video segmentation, radiographs, pathology slides and more!

Super excited to introduce SAM2 Studio! 🚀🤖 I've been getting a lot of questions lately on supporting AI inference tailored for patient data and sensitive workflows. We optimized SAM2 to run completely on-device in real time for all of your medical segmentation workflows - including surgical video segmentation, radiographs, pathology slides and more!

Cyril Zakka, MD

19,814 次观看 • 1 年前

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: Highlights: 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

Bo Wang

178,455 次观看 • 1 年前

Cyansdk is a free Blender AI motion capture plugin that runs locally on your computer. It requires 8GB of GPU memory for real-time processing and has a model size of 4.2GB. It supports real-time motion capture via webcam and video upload.

Cyansdk is a free Blender AI motion capture plugin that runs locally on your computer. It requires 8GB of GPU memory for real-time processing and has a model size of 4.2GB. It supports real-time motion capture via webcam and video upload.

CYANPUPPETS

16,201 次观看 • 1 年前

zero-shot image segmentation with Florence-2 + SAM-2 combo just added new mode to my Hugging Face; now you can run open vocabulary detection with Florence-2 + box to mask with SAM2 link:

zero-shot image segmentation with Florence-2 + SAM-2 combo just added new mode to my Hugging Face; now you can run open vocabulary detection with Florence-2 + box to mask with SAM2 link:

SkalskiP

66,010 次观看 • 1 年前

✨ CVPR 2025 highlight: A Distractor-Aware Memory for Visual Object Tracking with SAM2 the authors propose a new distractor-aware memory model for SAM2 and an introspection-based update strategy that jointly addresses the segmentation accuracy as well as tracking robustness 🏡 (1/n)🧵👇

✨ CVPR 2025 highlight: A Distractor-Aware Memory for Visual Object Tracking with SAM2 the authors propose a new distractor-aware memory model for SAM2 and an introspection-based update strategy that jointly addresses the segmentation accuracy as well as tracking robustness 🏡 (1/n)🧵👇

GeekyRakshit (e/mad)

32,669 次观看 • 1 年前

30 minutes of video that teach the AI stack behind basketball prediction systems on Polymarket one trader pulled $1.44M in 2 months running exactly this Python + RF-DETR + SAM2 builds player tracking, jersey number recognition, and shot classification from raw match footage Same stack powers the prediction systems in the article below Bookmark this & give it 30 minutes today

30 minutes of video that teach the AI stack behind basketball prediction systems on Polymarket one trader pulled $1.44M in 2 months running exactly this Python + RF-DETR + SAM2 builds player tracking, jersey number recognition, and shot classification from raw match footage Same stack powers the prediction systems in the article below Bookmark this & give it 30 minutes today

Paone

114,033 次观看 • 2 个月前

CVPR 2025 papers pt. 2 - SAMWISE SAMWISE adds language understanding and temporal reasoning to SAM2; you can segment and track objects in videos just by describing them more papers: ↓ more

CVPR 2025 papers pt. 2 - SAMWISE SAMWISE adds language understanding and temporal reasoning to SAM2; you can segment and track objects in videos just by describing them more papers: ↓ more

SkalskiP

20,528 次观看 • 1 年前

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Why can't “world models” just be sim? A real-time real2sim demo in the upcoming “ManiDreams” Foundation Stereo + SAM2 + Newton = Generalizable 3D physics prediction in a fast (15FPS) and lightweight (3070) way. No data or object mesh needed

Vector Wang

30,474 次观看 • 3 个月前

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

armistice

691,529 次观看 • 6 个月前

Apache 2.0 license🔥 On-device deployment ready Extends SAM2 for tracking objects in videos 🔥 Click-to-segment support EdgeTAM by Meta !

Apache 2.0 license🔥 On-device deployment ready Extends SAM2 for tracking objects in videos 🔥 Click-to-segment support EdgeTAM by Meta !

Gradio

23,301 次观看 • 1 年前

🇳🇱🗽 This is ByteDance's Seedance 2.0 with my New Amsterdam (current day New York City) Simulator prompt Unlike previous models like Seedance 1.5 (which would add windmills that didn't look Dutch), it really accurately portrays the city as it was in 1670 It's very impressive and because it takes reference image/video/audio, you can put yourself in it like I did here Only thing bad I see is some distortion in is some of the text which other video models seem to do better now, but yes it's very impressive This is purposely made to look a bit like a game, so it can do more photorealism than this actually

🇳🇱🗽 This is ByteDance's Seedance 2.0 with my New Amsterdam (current day New York City) Simulator prompt Unlike previous models like Seedance 1.5 (which would add windmills that didn't look Dutch), it really accurately portrays the city as it was in 1670 It's very impressive and because it takes reference image/video/audio, you can put yourself in it like I did here Only thing bad I see is some distortion in is some of the text which other video models seem to do better now, but yes it's very impressive This is purposely made to look a bit like a game, so it can do more photorealism than this actually

@levelsio

630,498 次观看 • 4 个月前

The free UE5.5 AI motion capture plugin is compatible with Unity, Blender, and VMC. It supports both real-time motion capture via webcam and video uploads to generate 3D motion data. Powered by a 1-billion-parameter motion model running locally on your computer, it requires 8GB of VRAM for real-time processing. Compatible with Nvidia, AMD, and Intel GPUs, it can leverage NVIDIA CUDA to significantly boost graphics computation efficiency.

The free UE5.5 AI motion capture plugin is compatible with Unity, Blender, and VMC. It supports both real-time motion capture via webcam and video uploads to generate 3D motion data. Powered by a 1-billion-parameter motion model running locally on your computer, it requires 8GB of VRAM for real-time processing. Compatible with Nvidia, AMD, and Intel GPUs, it can leverage NVIDIA CUDA to significantly boost graphics computation efficiency.

CYANPUPPETS

17,807 次观看 • 1 年前

This new AI image generator is impressive. You can now create an image based on a simple sketch and text prompt.

This new AI image generator is impressive. You can now create an image based on a simple sketch and text prompt.

Rowan Cheung

543,193 次观看 • 3 年前

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!

Justine Moore

28,574 次观看 • 9 个月前

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

SkalskiP

124,358 次观看 • 1 年前

I can't wait to get my hands on this one. It's called "Rerender A Video: Zero-shot Text-guided Video-to-video Translation" It takes an input video and re-renders it with your prompt without the flicker and weirdness we get from most current models.

I can't wait to get my hands on this one. It's called "Rerender A Video: Zero-shot Text-guided Video-to-video Translation" It takes an input video and re-renders it with your prompt without the flicker and weirdness we get from most current models.

Matt Wolfe

239,174 次观看 • 3 年前

Blender AI Motion Capture Plugin — Connects to a 1080P webcam and runs locally on your computer. Powered by a 1-billion-parameter model, it requires an 8GB VRAM GPU for real-time processing. Supports both real-time capture and video upload. The full-featured version currently supports NVIDIA CUDA only, and requires DX11 or above.

Blender AI Motion Capture Plugin — Connects to a 1080P webcam and runs locally on your computer. Powered by a 1-billion-parameter model, it requires an 8GB VRAM GPU for real-time processing. Supports both real-time capture and video upload. The full-featured version currently supports NVIDIA CUDA only, and requires DX11 or above.

CYANPUPPETS

58,611 次观看 • 1 年前

Full article capture to Notion on iPhone! This is a super early look at Flylighter on iOS. My team got this initial test build of the app up and running in a single month. Absolutely incredible. Next steps: ✅ Speed upgrades ✅ More capture modes - text highlights, voice recordings ✅ Capture history (so you can send a highlight to a previously captured page) Soon, you’ll have a full set of tools for capturing any idea or resource you find to Notion, instantly. Less friction = more action 💪

Full article capture to Notion on iPhone! This is a super early look at Flylighter on iOS. My team got this initial test build of the app up and running in a single month. Absolutely incredible. Next steps: ✅ Speed upgrades ✅ More capture modes - text highlights, voice recordings ✅ Capture history (so you can send a highlight to a previously captured page) Soon, you’ll have a full set of tools for capturing any idea or resource you find to Notion, instantly. Less friction = more action 💪

Thomas Frank

20,760 次观看 • 2 年前