Mastodawn

Automation is moving from “simple pick-and-place” to human-like handling. 🤖🖐️
know more:https://zurl.co/nqpPc
#Smidmart #Cobots #DexterousGripper #TactileSensors #Robotics #MachineVision #3DVision #IndustrialAI #FlexibleAutomation #PickAndPlace #AssemblyAutomation

Technische Universität München Mar 13

Researchers, including Benjamin Bogenberger, developed a robot that combines #LanguageModels with #3Dvision to locate misplaced objects by building a spatial map and estimating likely locations: http://go.tum.de/730486

#Robotics #AI

📷A. Schmitz

Search robot thinks for itself

A robot that can locate lost items on command – this is the latest development at the Technical University of Munich (TUM). It combines knowledge from…

sayzard Feb 23

Framer (@Framer_X)

이미지를 업로드하고 3D 공간에서 카메라를 움직이면 완전히 새로운 시점의 이미지를 생성할 수 있는 무료 도구가 공개되었습니다. 2D 이미지를 3D 장면으로 변환하는 혁신적인 비전 AI 응용 사례입니다.

https://x.com/Framer_X/status/2025912264256307447

#ai #3dvision #imagetools #innovation

Framer 🇱🇹 (@Framer_X) on X

This tool is insane. Upload any image. Move camera in 3D space. And get a completely new camera angle 🤯 Also it’s free! 👇

X (formerly Twitter)

sayzard Feb 22

田中義弘 | taziku CEO / AI × Creative (@taziku_co)

Seeed Studio가 Depth Anything V3와 NVIDIA Jetson AGX Orin을 결합해 단일 RGB 카메라만으로 로봇에 3D 인식 능력을 부여하는 솔루션을 공개했다. 이 기술은 고가의 센서나 장비 없이도 단안(depth) 추정(monocular depth) 기반으로 2D 이미지에서 실시간으로 거리 정보를 계산해 3D 공간 인식을 가능하게 한다. AI 기반의 최적화로 로봇 비전의 패러다임을 바꾸는 혁신적 접근이다.

https://x.com/taziku_co/status/2025499579245035744

#robotics #3dvision #depthestimation #ai #edge

田中義弘 | taziku CEO / AI × Creative (@taziku_co) on X

Depth Anything V3 × Jetson AGX Orin。 RGBカメラ1台だけでロボットに3D視覚を持たせる。特殊な機材不要。Monocular depthで2D画像からリアルタイムに奥行きを推定。「高価機材前提の3D認識」から、「AI推論＋最適化前提の3D認識」へのシフト。 via：@seeedstudio

X (formerly Twitter)

Smidmart Feb 17

Automation is moving from “perfectly placed parts” to real-world randomness — mixed bins, uneven shapes, variable orientation.
know more: https://zurl.co/3Skrb
#Smidmart #SmartGrippers #Cobots #Robotics #MachineVision #3DVision

cesium Oct 24

Now that I have a mental model for 3D shapes (not a visual perception from the eyes, but an inner representation that I can imagine/handle as volumes instead of as pictures/lines) I can better understand how not straightforward it is to "draw what you see"

to the point that I have to consciously switch between modes, and get (back) to the flattened perception to be able to draw as I am used to

#drawing #3DVision #perception

Harald Klinke Sep 12, 2025

OmniEVA: Bridging the 2D–3D Gap in Embodied AI

New paper introduces OmniEVA, a versatile embodied planner that pushes the boundaries of multimodal large language models (MLLMs) for robotics and spatial reasoning.

Results: OmniEVA achieves state-of-the-art performance across 2D/3D reasoning benchmarks and outperforms existing models in object navigation tasks.

Paper: https://arxiv.org/pdf/2509.09332v1
Project: https://omnieva.github.io/

#EmbodiedAI #Robotics #LLM #MLLM #3DVision #AIResearch #AIPlanning

💧🌏 Greg Cocks Nov 26, 2024

Building A Large Geospatial Model To Achieve Spatial Intelligence – Niantic Labs
--
https://nianticlabs.com/news/largegeospatialmodel/ <-- shared technical details
--
https://youtu.be/2mx_x9cMOaY?si=zKqHb_6KDyGKT14H <-- shared Niantic video – 5 Minute Neural Mapping
--
#GIS #spatial #mapping #pokémon #Pokemon #PokemonGO #largegeospatialmodel #model #modeling #algorithm #spatialintelligence #neuralnetwork #deeplearning #LargeGeospatialModel #LGM #AR #spatialperception #AI #VisualPositioningSystem #VPS #robotics #LargeLanguageModel #LLMs #3d #3dvisualisation #model #modeling #3dassets #3dvision
@niantic @NianticSpatial

Building a Large Geospatial Model to Achieve Spatial Intelligence

At Niantic, we are pioneering the concept of a Large Geospatial Model that will use large-scale machine learning to understand a scene and connect it to millions of other scenes globally.

Nicole Hennig Oct 8, 2024

Apple releases Depth Pro, an AI model that rewrites the rules of 3D vision https://venturebeat.com/ai/apple-releases-depth-pro-an-ai-model-that-rewrites-the-rules-of-3d-vision/ #AI #Apple #3dVision

Apple releases Depth Pro, an AI model that rewrites the rules of 3D vision

Apple's Depth Pro AI model sets a new standard in 3D depth estimation, offering high-resolution, real-time depth mapping from a single image without camera metadata—transforming industries like AR, autonomous vehicles, and more.

VentureBeat

Slash Insider Jan 11, 2024

#ABB has acquired Swiss start-up Sevensense to enhance industrial robot mobility using #AI and #3D vision. The #technology allows #robots to move independently in factories, improving flexibility and efficiency.

https://www.slashinsider.com/abb-acquires-sevensense-robot-mobility-3d-ai/

#TechNews #Robotics #3dvision #automation #technology

ABB Acquires Sevensense: Eyes And Brains For Industrial Robots

ABB has acquired Swiss start-up Sevensense to enhance industrial robot mobility using AI and 3D vision. The technology allows robots to move independently in factories, improving flexibility and efficiency.

Slash Insider