computer-vision

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

This repository is a curated collection of the most exciting and influential CVPR 2023 papers. 🔥 [Paper + Code]

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

[CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

A hub for various industry-specific schemas to be used with VLMs.

Cool experiments at the intersection of Computer Vision and Sports ⚽🏃

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

Python + Inference - Model Deployment library in Python. Simplest model inference server ever.

Fixes AI pixel art images, video, or sprite web uploads

A simple "Be My Eyes" web app with a llama.cpp/llava backend

Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ Star to support our work!

⚠️ Legacy repository for Geti v2.x. For Geti v3.0+, visit https://github.com/open-edge-platform/geti

Official Ultralytics YOLO Flutter plugin for real-time inference on Android and iOS across major vision tasks.

Mixture of Diffusers for scene composition and high resolution image generation

This is the official repository for the paper "Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing". ICCV 2023

🎨 Ready-to-use DeepSeek-OCR Web UI | Modern Interface | 7 Recognition Modes | Batch Processing | Real-time Logging | Fully Responsive

Python library & framework to build custom translators for the hearing-impaired and translate between Sign Language & Text using Artificial Intelligence.

[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion