Forem

# computervision

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Revealing the Unseen: AI-Powered Super-Resolution from Extreme Noise by Arvind Sundararajan

Revealing the Unseen: AI-Powered Super-Resolution from Extreme Noise by Arvind Sundararajan

Comments
2 min read
Clarity From Chaos: Super-Resolution That Thrives on Noise

Clarity From Chaos: Super-Resolution That Thrives on Noise

Comments
2 min read
3D Scanning Revolution: Reconstruct Anything, Anywhere, No Markers Required!

3D Scanning Revolution: Reconstruct Anything, Anywhere, No Markers Required!

Comments
2 min read
Object Genesis: Reconstructing Reality on the Fly by Arvind Sundararajan

Object Genesis: Reconstructing Reality on the Fly by Arvind Sundararajan

Comments
2 min read
Snap & Splat: Turn Everyday Objects into 3D Models with Your Phone

Snap & Splat: Turn Everyday Objects into 3D Models with Your Phone

Comments
2 min read
Creating a Libras Recognizer with Artificial Intelligence and Teachable Machine
Cover image for Creating a Libras Recognizer with Artificial Intelligence and Teachable Machine

Creating a Libras Recognizer with Artificial Intelligence and Teachable Machine

Comments
6 min read
Image Labeling Tools: A Simple Guide for Beginners
Cover image for Image Labeling Tools: A Simple Guide for Beginners

Image Labeling Tools: A Simple Guide for Beginners

Comments
5 min read
Lost in Translation: Unmasking Cultural Blind Spots in AI Video Analysis

Lost in Translation: Unmasking Cultural Blind Spots in AI Video Analysis

Comments
2 min read
Unlocking Musical DNA: Seeing Music Through Movement by Arvind Sundararajan

Unlocking Musical DNA: Seeing Music Through Movement by Arvind Sundararajan

1
Comments
2 min read
Video AI's Cultural Blind Spot: Why Your Models Might Be Misunderstanding the World

Video AI's Cultural Blind Spot: Why Your Models Might Be Misunderstanding the World

Comments
2 min read
The Cultural Iceberg: Unmasking Bias in Video AI

The Cultural Iceberg: Unmasking Bias in Video AI

Comments
2 min read
Seeing the Future: Mastering Action Recognition with Recurrence-Complete Architectures

Seeing the Future: Mastering Action Recognition with Recurrence-Complete Architectures

Comments
2 min read
Unlocking Image Understanding: A New Path to Visual AI for Everyone

Unlocking Image Understanding: A New Path to Visual AI for Everyone

Comments
2 min read
Visual Echo: When Images Start Talking Back

Visual Echo: When Images Start Talking Back

Comments
2 min read
Understanding Pose Estimation: How Computers See Human Movement
Cover image for Understanding Pose Estimation: How Computers See Human Movement

Understanding Pose Estimation: How Computers See Human Movement

Comments
5 min read
Iris ID: Pocket-Sized Security, Future-Proof Protection

Iris ID: Pocket-Sized Security, Future-Proof Protection

Comments
2 min read
Rewind & Relive: Reconstructing Surgery from Any Angle

Rewind & Relive: Reconstructing Surgery from Any Angle

Comments
2 min read
Synchronizing RGB, LiDAR & ToF in one platform TEMAS– our journey from KI Palooza to Kickstarter

Synchronizing RGB, LiDAR & ToF in one platform TEMAS– our journey from KI Palooza to Kickstarter

Comments
2 min read
See Through Their Eyes: Reconstructing Surgery from Any Angle by Arvind Sundararajan

See Through Their Eyes: Reconstructing Surgery from Any Angle by Arvind Sundararajan

Comments
2 min read
Spatial Sense: Extracting the 'Where' and 'How' from Vision-Language Models by Arvind Sundararajan

Spatial Sense: Extracting the 'Where' and 'How' from Vision-Language Models by Arvind Sundararajan

Comments
2 min read
Radiomics in Breast Cancer – Part 1: Exploring the CBIS-DDSM Dataset

Radiomics in Breast Cancer – Part 1: Exploring the CBIS-DDSM Dataset

Comments
6 min read
Lost in Translation: When Video AI Doesn't Get the Joke (Or the Culture)

Lost in Translation: When Video AI Doesn't Get the Joke (Or the Culture)

1
Comments
2 min read
From Photo to Fab: AI Cracks the Code to Instant 3D Models

From Photo to Fab: AI Cracks the Code to Instant 3D Models

Comments
2 min read
Second Internship not so Bad
Cover image for Second Internship not so Bad

Second Internship not so Bad

Comments
2 min read
Generating Synthetic RTL OCR Data for Donut with SynthDoG-RTL
Cover image for Generating Synthetic RTL OCR Data for Donut with SynthDoG-RTL

Generating Synthetic RTL OCR Data for Donut with SynthDoG-RTL

Comments
2 min read
loading...