DEV Community

#computervision

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Lịch Sá»­ OCR vĂ  Sá»± Ra Đời KhĂĄi Niệm Vision-First OCR

Lịch Sá»­ OCR vĂ  Sá»± Ra Đời KhĂĄi Niệm Vision-First OCR

Comments
12 min read
Evaluate the whole setup, not just the model: a practical workflow for video VLMs

Evaluate the whole setup, not just the model: a practical workflow for video VLMs

Comments
3 min read
LunarSite: An end-to-end ML pipeline for lunar south pole landing site selection

LunarSite: An end-to-end ML pipeline for lunar south pole landing site selection

Comments
16 min read
Using the channels-last memory format reduced the latency of our conversation backbone by 22%

Using the channels-last memory format reduced the latency of our conversation backbone by 22%

1
Comments
4 min read
The SDXL VAE overflow that decoded black images in fp16

The SDXL VAE overflow that decoded black images in fp16

1
Comments
4 min read
Unifying image inputs across three vision providers behind Bifrost

Unifying image inputs across three vision providers behind Bifrost

Comments
4 min read
Identity Consistency Is the Hard Part of Two-Person Image Generation

Identity Consistency Is the Hard Part of Two-Person Image Generation

2
Comments
2 min read
The seam our tiled upscaler left on every 4K product render

The seam our tiled upscaler left on every 4K product render

Comments
4 min read
I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

Comments
3 min read
Replacing a Slow QR + Edge Detection Pipeline with a Fast ArUco-Based Vision System

Summer Bug Smash: Clear the Lineup 🐛đŸ›č

Replacing a Slow QR + Edge Detection Pipeline with a Fast ArUco-Based Vision System

3
Comments
2 min read
Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Comments
4 min read
I Taught a Security Camera to Say "I Don't Know" — and It Got More Useful, Not Less

I Taught a Security Camera to Say "I Don't Know" — and It Got More Useful, Not Less

Comments 7
8 min read
I Built a Real-Time Perception Stack on CARLA. Here Is What Actually Happened.

I Built a Real-Time Perception Stack on CARLA. Here Is What Actually Happened.

3
Comments
6 min read
How I Built Production-Grade AI Systems While Still a Student

How I Built Production-Grade AI Systems While Still a Student

Comments
1 min read
A Hands-On Guide to kalbee: Your First Kalman Filter (and Beyond)

A Hands-On Guide to kalbee: Your First Kalman Filter (and Beyond)

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