Загрузка видео...

Не удалось загрузить видео

На главную

Instance vs semantic segmentation difference | Ultralytics🚀 🧩Instance segmentation answers: “Which pixels belong to each object?” 🎨Semantic segmentation answers: “Which pixels belong to each class?” #segmentation #MachineLearning #AI

muhammdrizwanmr's profile picture

Muhammad Rizwan Munawar

1,890 subscribers

16,764 просмотров • 13 дней назад •via X (Twitter)

Наука и технологии#segmentation#MachineLearning#AI
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️
0:15

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️

AI at Meta

3,570,426 просмотров • 3 лет назад

Live AI Object Segmentation with the Raspberry Pi 5 and the HAILO AI Accelerator Hat+ with 26 TOPS
0:18

Live AI Object Segmentation with the Raspberry Pi 5 and the HAILO AI Accelerator Hat+ with 26 TOPS

SparkLab

61,819 просмотров • 2 месяцев назад

YOLOE-26 released by Ultralytics support text + visual prompts 🤯 This was a part of the YOLO26 release. It's a zero-shot, promotable model, almost like YOLO-World, but it also offers real-time object segmentation. Highlights👇 #AI #MachineLearning #YOLOE
0:15

YOLOE-26 released by Ultralytics support text + visual prompts 🤯 This was a part of the YOLO26 release. It's a zero-shot, promotable model, almost like YOLO-World, but it also offers real-time object segmentation. Highlights👇 #AI #MachineLearning #YOLOE

Muhammad Rizwan Munawar

35,311 просмотров • 3 месяцев назад

Occlusion is still a challenge for SAM2. Video object segmentation is not solved yet
0:10

Occlusion is still a challenge for SAM2. Video object segmentation is not solved yet

Yu Xiang

53,676 просмотров • 1 год назад

So I had a free time and I decided to train a custom segmentation machine learning model on road lane. I combined it with Snap AR sky segmentation. Let me know what you think guys. #AugmentedReality #ar #ai
0:18

So I had a free time and I decided to train a custom segmentation machine learning model on road lane. I combined it with Snap AR sky segmentation. Let me know what you think guys. #AugmentedReality #ar #ai

Ibrahim Boona

12,419 просмотров • 3 лет назад

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.
0:18

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

AK

69,542 просмотров • 2 лет назад

Run promptable segmentation with Ultralytics YOLO26-E! 🧠 Segment objects using natural language prompts with YOLO26-E, ideal for flexible visual search, rapid annotation, and interactive computer vision workflows. Get started ➡️ #Ultralytics #YOLO26 #AI #Research
0:16

Run promptable segmentation with Ultralytics YOLO26-E! 🧠 Segment objects using natural language prompts with YOLO26-E, ideal for flexible visual search, rapid annotation, and interactive computer vision workflows. Get started ➡️ #Ultralytics #YOLO26 #AI #Research

Ultralytics

34,316 просмотров • 2 месяцев назад

From 2D to 3D segmentation: theory and applications of u-Segment3D by Felix Zhou et al.
0:14

From 2D to 3D segmentation: theory and applications of u-Segment3D by Felix Zhou et al.

Reto Fiolka

17,593 просмотров • 2 лет назад

a conceptual ui prototype of segmentation triggered by mouse movement, without prompting:
0:13

a conceptual ui prototype of segmentation triggered by mouse movement, without prompting:

Kat ⊷ the Poet Engineer

194,814 просмотров • 8 месяцев назад

Sora 2 can make a depth map, heat map, edge map and segmentation view, simultaneously in a grid. > start with a close up view of a woman in a studio, then split into a 2x2 grid showing in each cell the depth map, heat map, edge detection and segmentation of the scene
0:10

Sora 2 can make a depth map, heat map, edge map and segmentation view, simultaneously in a grid. > start with a close up view of a woman in a studio, then split into a 2x2 grid showing in each cell the depth map, heat map, edge detection and segmentation of the scene

fofr

39,777 просмотров • 9 месяцев назад

We are presenting **SAD** (Segment Any RGBD): SAD is able to perform 3D segmentation (segment out any 3D object) with RGBD inputs (or rendered depth images only). - Code: - Demo Hugging Face:
0:11

We are presenting **SAD** (Segment Any RGBD): SAD is able to perform 3D segmentation (segment out any 3D object) with RGBD inputs (or rendered depth images only). - Code: - Demo Hugging Face:

Ziwei Liu

195,642 просмотров • 3 лет назад

Segment Anything is fun and powerful but still requires full mask annotation for supervised training. Our new work MaskFreeVIS appearing at #CVPR2023 shows we can get accurate video instance segmentation WITHOUT any video or image mask annotations. More at
0:20

Segment Anything is fun and powerful but still requires full mask annotation for supervised training. Our new work MaskFreeVIS appearing at #CVPR2023 shows we can get accurate video instance segmentation WITHOUT any video or image mask annotations. More at

Fisher Yu

41,103 просмотров • 3 лет назад

Created a quick VFX to make Wimbledon more green🌱 Using Camera Pose Estimation, body & ball segmentation to incorporate the grass simulation 🙂
0:12

Created a quick VFX to make Wimbledon more green🌱 Using Camera Pose Estimation, body & ball segmentation to incorporate the grass simulation 🙂

Alexandre Devaux

19,557 просмотров • 1 год назад

🚀 Wan 2.6 is now live on fal ! • Text-to-Video & Image-to-Video up to 1080p • Up to 15 second generations • Multi-shot video with intelligent scene segmentation • Import your own audio • Reference-to-Video - use 1-3 reference videos for character/object consistency
0:15

🚀 Wan 2.6 is now live on fal ! • Text-to-Video & Image-to-Video up to 1080p • Up to 15 second generations • Multi-shot video with intelligent scene segmentation • Import your own audio • Reference-to-Video - use 1-3 reference videos for character/object consistency

fal

64,542 просмотров • 6 месяцев назад

Core AI: Realtime video image detection, tracking, and segmentation with SAM 3 and RF-DETR. All running on-device. I will share the code in the comments.
0:18

Core AI: Realtime video image detection, tracking, and segmentation with SAM 3 and RF-DETR. All running on-device. I will share the code in the comments.

Amos Gyamfi

15,373 просмотров • 10 дней назад

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI
0:15

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Muhammad Rizwan Munawar

30,677 просмотров • 3 месяцев назад

YOLOv9-Pose-DepthAnythingV2-Segmentation-Wholebody34-E できた。CUDAで Eサイズを味見したので遅い。
0:18

YOLOv9-Pose-DepthAnythingV2-Segmentation-Wholebody34-E できた。CUDAで Eサイズを味見したので遅い。

Super PINTO

13,385 просмотров • 1 год назад

🚀 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
0:22

🚀 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

178,481 просмотров • 1 год назад

RF-DETR is now available in Hugging Face transformers state of the art in both detection and segmentation, outperforming YOLO architectures - checkpoints: - demo: - docs:
0:11

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

SkalskiP

79,277 просмотров • 1 месяц назад

another experiment with fruit, computer vision, and projection mapping live object detections (roboflow RF-DETR model) are used to control the animated scene (threejs) i also added mediapipe segmentation to the pipeline to create collisions with my silhouette, but i haven't gotten a hang of it yet more experiments are underway
0:16

another experiment with fruit, computer vision, and projection mapping live object detections (roboflow RF-DETR model) are used to control the animated scene (threejs) i also added mediapipe segmentation to the pipeline to create collisions with my silhouette, but i haven't gotten a hang of it yet more experiments are underway

AA

21,581 просмотров • 1 месяц назад