AIagent.at πŸ€– AI News10h ago
Netflix has open-sourced VOID, an AI model that removes objects from videos along with their physical interactions. When a person holding an object is removed, the object falls naturally rather than floating. Built on Alibaba's CogVideoX, it uses a quadmask to understand what should physically change after removal. The code and weights are on Hugging Face. https://www.marktechpost.com/2026/04/04/netflix-ai-team-just-open-sourced-void-an-ai-model-that-erases-objects-from-videos-physics-and-all/ #AIagent #AI #GenAI #ComputerVision #Netflix
Netflix AI Team Just Open-Sourced VOID: an AI Model That Erases Objects From Videos β€” Physics and All

Netflix AI Research Team Just Open-Sourced VOID: an AI Model That Erases Objects From Videos β€” Physics and All

MarkTechPost
sayzard18h ago

Ultralytics (@ultralytics)

Ultralytics μœ ν‹Έλ¦¬ν‹°λ₯Ό μ‚¬μš©ν•΄ λ°”μš΄λ”© λ°•μŠ€ μ’Œν‘œλ‘œλΆ€ν„° 폭, 높이 λ“± λ°•μŠ€ 속성을 κ³„μ‚°ν•˜λŠ” 방법을 μ†Œκ°œν–ˆλ‹€. 객체 μΈ‘μ •κ³Ό μ»€μŠ€ν…€ 컴퓨터 λΉ„μ „ μ›Œν¬ν”Œλ‘œμ— λ°”λ‘œ ν™œμš©ν•  수 μžˆλŠ” μ‹€μš©μ μΈ κΈ°λŠ₯으둜, κ°œλ°œμžκ°€ 탐지 κ²°κ³Όλ₯Ό ν›„μ²˜λ¦¬ν•  λ•Œ μœ μš©ν•˜λ‹€.

https://x.com/ultralytics/status/2040102052609581441

#ultralytics #computervision #boundingbox #objectdetection #utilities

Ultralytics (@ultralytics) on X

Extract bounding box dimensions using Ultralytics utilities! πŸ“ Compute width, height, and other box properties directly from bounding box coordinates, useful for object measurements and custom computer vision workflows. Learn more ➑️ https://t.co/TBOBex2np0 #Ultralytics

X (formerly Twitter)
Stephen Blum1d ago

Use pose tracking to overlay a fake skeleton x ray effect.

#computervision #imageprocessing #pose

sayzard2d ago

Ultralytics (@ultralytics)

Ultralytics YOLO26의 segmentation κΈ°λŠ₯을 ν™œμš©ν•΄ 식물 잎의 병변 λΆ€μœ„λ₯Ό νƒμ§€Β·λΆ„λ¦¬ν•˜λŠ” 데λͺ¨λ₯Ό μ†Œκ°œν•œλ‹€. μž‘λ¬Ό λͺ¨λ‹ˆν„°λ§, μ‘°κΈ° 병해 진단, 정밀농업 μ›Œν¬ν”Œλ‘œμ— μ ν•©ν•œ AI λΉ„μ „ 적용 사둀닀.

https://x.com/ultralytics/status/2039735971260875025

#ultralytics #yolo26 #segmentation #precisionagriculture #computervision

Ultralytics (@ultralytics) on X

Segment leaf disease with Ultralytics YOLO26! πŸƒ Identify and isolate infected regions on plant leaves using the YOLO26 segmentation task, ideal for crop monitoring, early disease detection, and precision agriculture workflows. Explore more ➑️ https://t.co/SM5vNNTmuH

X (formerly Twitter)
OpenCV2d ago
On today's live stream we gave you a preview of the speakers and talks at OpenCV's upcoming conference, OSCCA! See what you can expect in Los Angeles this May https://www.youtube.com/watch?v=-jG7CJZFVMQ #OpenCV #ComputerVision #AI
OpenCV-SID Conference on Computer Vision & AI (OSCCA) 2026 Preview

YouTube
Winbuzzer2d ago

https://winbuzzer.com/2026/04/02/zai-launches-glm-5v-turbo-multimodal-vision-model-xcxwbn/

Z.ai Launches GLM-5V-Turbo Multimodal Vision Model

#AI #ZAI #Zhipu #GLM5VTurbo #GLM5VTurbo #ChinaAI #China #LLMs #MultimodalAI #AgenticAI #AIModels #ComputerVision #Glm5 #Openclaw #VisionCodingModel

sayzard2d ago

Ultralytics (@ultralytics)

Ultralytics YOLO26 κ²°κ³Όλ₯Ό 뢄석 κ·Έλž˜ν”„λ‘œ μ‹œκ°ν™”ν•˜λŠ” κΈ°λŠ₯을 μ†Œκ°œν•©λ‹ˆλ‹€. κ°μ§€λœ 객체 수, ν΄λž˜μŠ€λ³„ 좔이, ν™œλ™ νŒ¨ν„΄μ„ 차트둜 확인할 수 μžˆμ–΄ ꡐ톡 λͺ¨λ‹ˆν„°λ§, λ¦¬ν…ŒμΌ 뢄석, 슀마트 κ°μ‹œ λ“±μ—μ„œ μœ μš©ν•©λ‹ˆλ‹€.

https://x.com/ultralytics/status/2039376036274581816

#ultralytics #yolo #computervision #analytics #visualization

Ultralytics (@ultralytics) on X

Visualize Ultralytics YOLO26 results with analytical graphs! πŸ“Š Generate clear charts to track detected object counts, compare class trends, and analyze activity patterns. Ideal for traffic monitoring, retail analytics, and smart surveillance insights. Explore more ➑️

X (formerly Twitter)
Bodo Menke2d ago

OpenClaw mit Qwen3.5-35B-A3B

Damit geht dann jetzt auch Computer Vision.
Nur nicht sicher, ob ich zutreffend beschrieben bin…? ;-)

#OpenClaw #Qwen
#ComputerVision
#AI #KI

sayzard3d ago

AA (@measure_plan)

μžλ°”μŠ€ν¬λ¦½νŠΈ, μΊ”λ²„μŠ€, Roboflow RF-DETR, MediaPipe 포즈 νŠΈλž˜ν‚Ήμ„ ν™œμš©ν•΄ ν‘Έμ‹œμ—…κ³Ό ν”Œλž­ν¬λ‘œ μ‘°μž‘ν•˜λŠ” 동킀콩 μŠ€νƒ€μΌ ν”ΌνŠΈλ‹ˆμŠ€ κ²Œμž„μ„ λ§Œλ“€μ—ˆλ‹€. AI λΉ„μ „κ³Ό 체성 인식 κΈ°μˆ μ„ κ²°ν•©ν•œ ν₯미둜운 μΈν„°λž™ν‹°λΈŒ ν”„λ‘œμ νŠΈλ‹€.

https://x.com/measure_plan/status/2039412017002365359

#javascript #computervision #fitness #mediapipe #roboflow

AA (@measure_plan) on X

i made donkey kong but you play with pushups and planks and it's quite inconvenient made with javascript, canvas, roboflow RF-DETR (for banana detection), and mediapipe body pose tracking lmk if you want to play a few fitness games like this and i'll try to get these online

X (formerly Twitter)
Solomon3d ago

🧠 Meta releases SAM 3

Segment Anything Model 3 is live on HuggingFace. Achieves 75-80% of human performance on the new SA-CO benchmark (270K unique concepts, 50x larger than prior benchmarks).

If your stack touches vision β€” object detection, image editing, autonomous systems β€” this is worth evaluating.

Source: https://huggingface.co/facebook/sam3

#ComputerVision #MachineLearning #OpenSource #AILabs

facebook/sam3 Β· Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.