DEV Community

#computervision

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your CNN's Advantage Is One Assumption — and I Measured What Happens When It Breaks

Your CNN's Advantage Is One Assumption — and I Measured What Happens When It Breaks

Comments
6 min read
Pmw final portfolio · MD Humna Attique — PMW TechRealm Internship Portfolio

Pmw final portfolio · MD Humna Attique — PMW TechRealm Internship Portfolio

Comments
2 min read
Can image tokens cost less than text tokens - Explaining Gemini API Image Token Economics

Can image tokens cost less than text tokens - Explaining Gemini API Image Token Economics

Comments
7 min read
Classifying mud crab sex with YOLOv11 — when 200 images and messy real-world labels fight back

Classifying mud crab sex with YOLOv11 — when 200 images and messy real-world labels fight back

Comments
3 min read
Decoupling Physical Control and Reasoning: DeepMind's Gemini Robotics 2 Architecture

Decoupling Physical Control and Reasoning: DeepMind's Gemini Robotics 2 Architecture

Comments
5 min read
Segmentation Is Not the Finish Line

Segmentation Is Not the Finish Line

Comments
5 min read
The mAP50 That Lied to Me: A Debugging Story About On-Device Safety AI

The mAP50 That Lied to Me: A Debugging Story About On-Device Safety AI

Comments
5 min read
Case Study: Fixing a Failed 3D Reconstruction of Shalimar Gardens' Moorcroft Pavilion

Case Study: Fixing a Failed 3D Reconstruction of Shalimar Gardens' Moorcroft Pavilion

Comments
2 min read
AI Landscape Design in 2026: Why the Generative Model Is the Easy Part

AI Landscape Design in 2026: Why the Generative Model Is the Easy Part

Comments
5 min read
From 42 Points to 842: Debugging a CPU-Only 3D Reconstruction Pipeline

From 42 Points to 842: Debugging a CPU-Only 3D Reconstruction Pipeline

Comments
2 min read
Detecting Objects in Satellite Imagery with YOLOv8: xView + DOTA to YOLO in Practice

Detecting Objects in Satellite Imagery with YOLOv8: xView + DOTA to YOLO in Practice

1
Comments 3
5 min read
The Model Is the Easy Part: What a Real-Time Computer Vision Product Actually Takes

The Model Is the Easy Part: What a Real-Time Computer Vision Product Actually Takes

Comments
6 min read
The Master Woodworker

The Master Woodworker

2
Comments
3 min read
How Vision-Language Models Learned to Reason About Space (10 Papers, One Thread)

How Vision-Language Models Learned to Reason About Space (10 Papers, One Thread)

Comments
3 min read
We made our world model smaller and it got better. Then "efficient" attention made nothing faster.

We made our world model smaller and it got better. Then "efficient" attention made nothing faster.

1
Comments 1
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.