👁️ computer vision - alex · Scour

Automate Pothole Detection with RF-DETR & ByteTrack 📐Computational Geometry

blog.roboflow.com·5d

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models 🖼️Neural Art

Multi-scale fusion convolution network with progressive dilation for real-time salient object detection of surface defects on strip steel 🖼️Neural Art

Art’s hidden topology: A window into human perception 📈Information Aesthetics

journals.plos.org·5d

An Introduction to Exemplar Partitioning for Mechanistic Interpretability 🧠Meta-creativity

lesswrong.com·4d

AI Fusion Photography 🌱generative art

aifusionphotography.com·4d·Hacker News

Convolutional neural networks enable high-fidelity prediction of rotation-invariant properties of amorphous and crystalline materials 👓AR Development

link.aps.org·5d

What Matters in Practical Learned Image Compression 🌀Noise Algorithms

apple.github.io·6d·Hacker News

WildLife AI 👓AR Development

hackster.io·3d

A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition 🖼️Neural Art

Image to Video AI Generator Online (Website) 🖼️Neural Art

image-to-video.ai·5d

Condition-Embedded Visible-Infrared image dataset for typical ground features 📐Computational Geometry

PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning 👓AR Development

noahgolmant/pytorch-hessian-eigenthings: Efficient PyTorch Hessian eigendecomposition tools! 🌀Noise Algorithms

github.com·6d·Hacker News

MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes 🖼️Neural Art

HuggingFace #1 Paper of the Day by Solo Researcher 📚Programming language theory

huggingface.co·6d·Hacker News

SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution 👓AR Development

schmidhuber-problems/VISUAL_TOUR.md at main · cybertronai/schmidhuber-problems 🖼️Neural Art

RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition 👓AR Development

Energy-efficient traffic sign recognition using directly trained spiking neural networks and population decoding 🖼️Neural Art

frontiersin.org·5d

Sign up or log in to see more results

Log in to enable infinite scrolling